1504 Integrations with Python
View a list of Python integrations and software that integrates with Python below. Compare the best Python integrations as well as features, ratings, user reviews, and pricing of software that integrates with Python. Here are the current Python integrations in 2026:
-
1
Genesis Computing
Genesis Computing
Genesis Computing provides an enterprise AI platform built around autonomous “AI data agents” that automate complex data engineering and analytics workflows across an organization’s existing technology stack. It introduces a new category of AI knowledge workers that operate as autonomous agents capable of executing full data workflows rather than simply suggesting code or analysis. These agents can research data sources, ingest and transform datasets, map raw data from source systems to structured analytical targets, generate and run data pipeline code, create documentation, perform testing, and monitor pipelines in production environments. By handling these tasks end-to-end, the platform reduces the manual workload typically required to build and maintain data pipelines and analytics infrastructure.Starting Price: Free -
2
Gemini Embedding 2
Google
Gemini Embedding models, including the newer Gemini Embedding 2, are part of Google’s Gemini AI ecosystem and are designed to convert text, phrases, sentences, and code into numerical vector representations that capture their semantic meaning. Unlike generative models that produce new content, the embedding model transforms input data into dense vectors that represent meaning in a mathematical format, allowing computers to compare and analyze information based on conceptual similarity rather than exact wording. These embeddings enable applications such as semantic search, recommendation systems, document retrieval, clustering, classification, and retrieval-augmented generation pipelines. The model can process input in more than 100 languages and supports up to 2048 tokens per request, allowing it to embed longer pieces of text or code while maintaining strong contextual understanding.Starting Price: Free -
3
AgentMail
AgentMail
AgentMail is an API-first email platform designed to give artificial intelligence agents their own fully functional email inboxes, enabling them to communicate, send messages, and participate in email conversations autonomously. Instead of building on traditional email providers created for human users, it provides programmatic inboxes that can be created and managed directly through an API, allowing developers to assign email identities to AI agents in the same way a human would have a Gmail or Outlook account. Each agent receives its own inbox and email address, which can send, receive, and reply to messages while maintaining threaded conversations and persistent message history. It enables AI agents to read and interpret incoming emails, extract structured information from messages, and automatically generate responses or trigger workflows based on the content of the conversation.Starting Price: $20 per month -
4
GLM-5-Turbo
Z.ai
GLM-5-Turbo is a high-speed variant of Z.ai’s GLM-5 model, designed to deliver efficient and stable performance in agent-driven environments while maintaining strong reasoning and coding capabilities. It is optimized for high-throughput workloads, particularly long-chain agent tasks where multiple steps, tools, and decisions must be executed in sequence with reliability and low latency. It supports advanced agentic workflows, enabling systems to perform multi-step planning, tool calling, and task execution with improved responsiveness compared to larger flagship models. GLM-5-Turbo inherits core capabilities from the GLM-5 family, including strong reasoning, coding performance, and support for long-context processing, while focusing on optimization of core requirements such as speed, efficiency, and stability in production environments. It is designed to integrate with agent frameworks like OpenClaw, where it can coordinate actions, process inputs, and execute tasks.Starting Price: Free -
5
OneVPS
OneVPS
OneVPS is a cloud-based virtual private server platform designed to provide fast, scalable, and fully customizable hosting environments for websites and applications. It offers VPS solutions with dedicated resources such as Intel CPUs, SSD storage, configurable RAM, and flexible bandwidth, allowing users to tailor their server to specific performance needs. It emphasizes simplicity and speed, enabling users to deploy a server in as little as 60 seconds through a guided setup process, while still maintaining full root access and control over the environment. It supports a wide range of development stacks and applications, including Java, PHP, Python, and Ruby on Rails, and provides compatibility with control panels like cPanel for easier management. OneVPS is built for performance, featuring optimized infrastructure with ultra-low latency, global data center locations, and high-speed networking to ensure consistent uptime and fast load times worldwide.Starting Price: $5 per month -
6
TurboDocx
TurboDocx
TurboDocx is an AI-powered document automation and templating platform designed to help businesses rapidly create, customize, and manage professional documents and presentations using reusable templates, centralized content, and intelligent automation. It enables users to pull data from multiple sources, such as CRMs, meeting transcripts, and project tools, and automatically populate templates with accurate, up-to-date information, eliminating manual copy-paste work and reducing errors. It supports both AI-driven and manual workflows, allowing users to auto-fill variables, generate custom sections, and adapt tone and style, or assemble documents by selecting pre-approved content from a shared knowledge base to ensure brand consistency. It integrates with tools like Microsoft Word, PowerPoint, Google Docs, and cloud storage systems, allowing teams to work within familiar environments while automating document generation.Starting Price: $10 per month -
7
CoStrict
zgsm-ai
CoStrict is an enterprise-grade AI programming platform designed to assist developers throughout the entire software development lifecycle by combining code generation, coding assistance, code completion, and automated code review into a single integrated system. It introduces a “quality-first” development approach, where features like Strict Mode break down requirements into structured steps such as analysis, architecture design, task planning, and automated test generation before writing code, ensuring that outputs meet high standards from the start. It can analyze entire code repositories using retrieval-augmented techniques, allowing it to understand project context, reuse existing standards, and provide highly relevant suggestions and improvements. It includes an AI agent capable of generating code, answering questions, optimizing logic, and adding documentation in real time, while code completion features accelerate development.Starting Price: Free -
8
Claude Agent SDK
Claude
The Claude Agent SDK is a developer toolkit that enables the creation of autonomous AI agents powered by Claude, allowing them to perform real-world tasks beyond simple text generation by interacting directly with files, systems, and tools. It provides the same underlying infrastructure used by Claude Code, including an agent loop, context management, and built-in tool execution, and is available for use in Python and TypeScript. With this SDK, developers can build agents that read and write files, execute shell commands, search the web, edit code, and automate complex workflows without needing to implement these capabilities from scratch. It maintains persistent context and state across interactions, enabling agents to operate continuously, reason through multi-step problems, take actions, verify results, and iterate until tasks are completed.Starting Price: Free -
9
Microsoft Agent Framework
Microsoft
Microsoft Agent Framework is an open source SDK and runtime designed to help developers build, orchestrate, and deploy AI agents and multi-agent workflows using languages such as .NET and Python. It combines the simple agent abstractions of AutoGen with the enterprise-grade capabilities of Semantic Kernel, including session-based state management, type safety, middleware, telemetry, and broad model and embedding support, creating a unified platform for both experimentation and production use. It introduces graph-based workflows that give developers explicit control over how multiple agents interact, execute tasks, and coordinate complex processes, enabling structured orchestration across sequential, concurrent, or branching scenarios. It supports long-running and human-in-the-loop workflows through robust state management, allowing agents to maintain context, reason through multi-step problems, and operate continuously over time.Starting Price: Free -
10
EODHD
EODHD
EODHD is a financial data API platform that provides developers and analysts with access to a comprehensive range of global market data through a single, unified interface. It offers over 30 years of historical data along with real-time and intraday feeds across more than 60 stock exchanges, covering over 150,000 tickers, including stocks, ETFs, mutual funds, bonds, Forex pairs, and digital currencies. It delivers multiple types of datasets such as end-of-day prices, live OHLCV data, corporate actions like splits and dividends, financial news, technical indicators, macroeconomic data, and stock screeners, all accessible via REST APIs and WebSocket connections. It delivers multiple types of datasets such as end-of-day prices, live OHLCV data, corporate actions like splits and dividends, financial news, technical indicators, macroeconomic data, and stock screeners, all accessible via REST APIs and WebSocket connections.Starting Price: $19.99 per month -
11
Cosyra
Cosyra
Cosyra is a mobile-first cloud development environment that enables users to run AI-powered coding tools directly from their phone through a full Linux terminal. It allows developers to use tools such as Claude Code, Codex CLI, OpenCode, and Gemini CLI, all pre-installed and ready to run by simply adding an API key and opening the terminal. It provides an isolated Ubuntu container with essential development tools, including Node.js, Python, Git, tmux, and vim, along with 30 GB of persistent storage that contains data between sessions. Cosyra is designed to replicate the experience of working on a local machine, allowing users to build, test, and manage projects entirely from a mobile device. It supports workflows such as cloning repositories, reviewing pull requests, running tests, and deploying code, all within a persistent session that can hibernate and resume seamlessly.Starting Price: $29.99 per month -
12
Subconscious
Subconscious
Subconscious is a developer-first platform designed to build, deploy, and scale production-ready AI agents by handling the hardest parts of agent architecture automatically. It provides a complete agent system that manages context, orchestrates tools, and enables long-horizon reasoning, allowing developers to focus on defining goals and capabilities rather than stitching together complex infrastructure. It introduces a unified inference engine composed of a co-designed model and runtime that decomposes complex tasks, generates workflows dynamically, and executes multi-step reasoning without manual context engineering or multi-agent orchestration. Unlike traditional approaches that rely on chaining APIs and frameworks, Subconscious enables agents to take in goals and tools, then autonomously plan, reason, and act with minimal human intervention, effectively creating systems that can “get the job done” on their own.Starting Price: $2 per 1M tokens -
13
kubbi
kubbi
kubbi is a secure handoff layer for AI agents that enables the safe transfer of data, files, and execution results between different systems, agents, or humans through temporary, encrypted claim links. Instead of passing sensitive information directly through workflows, prompts, or logs, kubbi allows a producer to create a payload containing content or bundled files, assign a time-to-live, and generate a unique claim URL that can be shared with the next actor in the process. The consumer can then retrieve the payload on their own schedule, after which the data can expire automatically or be permanently destroyed based on configured retrieval limits. This approach reduces exposure of sensitive data across systems and prevents it from being logged, cached, or replayed unintentionally. kubbi supports multiple use cases such as transferring configuration files, datasets, reports, tokens, and other transient or sensitive data that should not remain in persistent systems.Starting Price: $19 per month -
14
InventDB
InventDB
InventDB is an encrypted JSON database that combines schema-free data storage with SQL querying capabilities, enabling developers to work with flexible data structures while retaining the power of relational querying. It is designed to support full ACID transactions, ensuring consistency, reliability, and durability of data operations even in complex or concurrent environments. It incorporates row-level encryption, allowing sensitive data to be protected at a granular level rather than relying solely on database-wide security, which enhances data privacy and control. In addition to its core database functionality, InventDB includes a built-in key-value cache to improve performance and speed up data access for frequently used information. It also integrates semantic capabilities, enabling more intelligent data retrieval and interactions beyond traditional query methods.Starting Price: $18 per month -
15
AnduinOS
AnduinOS
AnduinOS is a custom Ubuntu-based Linux distribution designed to provide a familiar, easy-to-use experience for users transitioning from other operating systems, particularly those accustomed to Windows. It offers a lightweight and efficient system with a relatively small installation image, allowing for quick setup and immediate usability without complex configuration. It features a GNOME-based desktop environment with a clean and intuitive interface that aligns with common user habits, reducing the learning curve and enabling fast adoption. Built on the Ubuntu ecosystem, AnduinOS is compatible with most Ubuntu packages, giving users access to a wide range of applications and tools while maintaining stability and flexibility. It emphasizes privacy and security by avoiding tracking, profiling, or data collection, ensuring that users remain anonymous within the system.Starting Price: Free -
16
TinyFish
TinyFish
TinyFish is an enterprise AI platform that builds and operates “enterprise web agents” designed to execute complex workflows directly across the web at massive scale. Instead of relying on APIs or manual processes, these agents interact with websites the way humans do, navigating interfaces, extracting data, and completing multi-step tasks across thousands of platforms simultaneously. It is built to handle the growing complexity of the modern web, where valuable data is often fragmented, hidden behind logins, or constantly changing, making traditional automation unreliable. TinyFish agents are powered by infrastructure that can learn, adapt, and scale, enabling them to maintain accuracy and reliability even as web environments evolve. It is designed around outcome-driven workflows rather than isolated tasks, meaning agents can execute entire processes such as pricing intelligence, inventory tracking, or market monitoring from start to finish.Starting Price: $1.50 per month -
17
GPT-5.5 Pro
OpenAI
GPT-5.5 Pro is an advanced AI model designed to handle complex, real-world work with greater autonomy and efficiency. It understands user intent quickly and can execute multi-step tasks such as coding, research, data analysis, and document creation with minimal guidance. The model is built to plan, use tools, and refine its outputs until tasks are complete. It excels in knowledge work, software development, and analytical problem-solving. With strong reasoning and persistence, GPT-5.5 Pro can manage long-running workflows across tools and systems. It delivers high-quality results while maintaining speed and efficiency. Overall, it enables individuals and teams to complete demanding tasks faster and more accurately.Starting Price: $30 per 1M tokens (input) -
18
ZenMux
ZenMux
ZenMux is an enterprise-grade AI gateway that provides a unified interface for accessing and orchestrating multiple leading large language models through a single account and API. Instead of managing separate providers, keys, and integrations, users can connect to top models from companies like OpenAI, Anthropic, Google, and others through one consistent system, fully compatible with existing protocols such as OpenAI and Gemini Enterprise Agent Platform. It eliminates the complexity of multi-provider setups by offering intelligent routing that automatically selects the most suitable model for each task based on cost, performance, and reliability. ZenMux emphasizes direct access to official providers and authorized cloud partners, ensuring that all outputs come from authentic, high-quality sources without proxies or degraded versions. One of its defining features is a built-in AI model insurance, which detects issues.Starting Price: $20 per month -
19
Outcron
Outcron
Outcron is a hosted job scheduler designed to replace traditional cron setups with a more reliable, managed system that removes the need for maintaining servers or patching together scripts. It provides a centralized platform where users can schedule and run critical jobs with built-in reliability, ensuring tasks execute consistently without manual oversight or infrastructure management. It supports multiple job types and offers a flexible scheduling system that goes beyond basic cron syntax, enabling more complex and adaptable workflows. A key feature is misfire recovery, which ensures that missed or failed jobs are automatically detected and retried, reducing the risk of silent failures that often occur in self-managed cron environments. Outcron also includes execution history and observability tools, allowing users to track every run, inspect logs, and understand how jobs behave over time.Starting Price: $69 per month -
20
Abliteration.ai
Abliteration.ai
Abliteration.ai is a developer-focused AI platform that provides access to unrestricted large language models combined with a policy control layer, allowing teams to define exactly how models should behave rather than relying on built-in provider restrictions. It offers an OpenAI-compatible API, enabling seamless integration into existing tools, SDKs, and workflows without requiring major changes to infrastructure. Abliteration.ai’s core concept is “unrestricted, not ungoverned,” meaning developers can use less-censored models while enforcing their own rules through a Policy Gateway that applies real-time controls such as allowing, blocking, redacting, or escalating outputs based on custom policies. These policies are written as code and can be audited, simulated, and deployed with features like shadow testing and rollback safeguards. Abliteration.ai supports advanced use cases such as security testing, red teaming, synthetic data generation, and specialized research workflows.Starting Price: $20 per month -
21
PyGPT
PyGPT
PyGPT is an open source, personal desktop AI assistant for Linux, Windows, and Mac, written in Python. It works similarly to ChatGPT, but locally on a desktop computer, with chat, vision, agents, image and video generation, tools, voice control, and more. PyGPT supports multiple models, including OpenAI GPT-5, GPT-4, o1, o3, o4, Google Gemini, Anthropic Claude, xAI Grok, Perplexity Sonar, DeepSeek, Mistral AI, and models accessible through Ollama and LlamaIndex. It offers 12 modes of operation, including chat, chat with files, realtime + audio, research, completion, image and video generation, vision, assistants, experts, computer use, agents, and autonomous mode. Users can chat with their own files and data using integrated LlamaIndex support. PyGPT includes built-in vector database support, automated files and data embedding, full conversation context, short- and long-term memory, internet access through Google, Microsoft Bing, and DuckDuckGo, plus speech synthesis and recognition.Starting Price: Free -
22
RailPush
RailPush
RailPush is a deployment platform that takes your code from repository to running app with builds, HTTPS, and a default URL out of the box. Connect your repo, deploy in minutes, and get a live URL, RailPush keeps deploys, data, and routing under one roof, letting users connect GitHub, describe what they need, and build, run, and front applications with defaults they can override. Every push builds, checks health, and rolls out, while the platform provides an instant URL with TLS and preview links. Users can create a first web service by connecting a GitHub repository, selecting a repo and branch, configuring build and start commands when needed, and creating a service that deploys automatically. RailPush auto-detects the runtime and generates an optimized Dockerfile, with support for Node.js, Python, Go, Ruby, Rust, Elixir, Java, and Docker. To skip configuration, users can deploy pre-configured stacks like Next.js + Postgres, Django + Redis, Rails, and more through templates.Starting Price: $4 per month -
23
Zavu
Zavu
Zavu is one API for all your messages, built to send and receive SMS, WhatsApp, Email, Voice, Telegram, and more from a single integration. It helps developers ship messaging instead of maintaining messaging infrastructure, replacing separate APIs, SDKs, auth models, webhook formats, sender setup, template approvals, and error handling with one SDK, one webhook format, and one dashboard. Zavu is also built for AI agents from day one: agents can send SMS, WhatsApp, Email, and Voice globally, while developers can use production-ready SDKs across languages such as Node.js, Python, Ruby, Go, PHP, and Java. Its Smart Send and AI Routing features pick SMS, WhatsApp, or Email per contact, choose the best or cheapest delivery path using platform-wide delivery intelligence, and fall back automatically when a channel fails. Context is preserved, delivery is deduplicated, and cost is tracked end-to-end across the fallback chain.Starting Price: $21 per month -
24
PRFlow
PRFlow
PRFlow is an AI code reviewer built to find the bugs that ship. It indexes your codebase, traces cross-file dependencies, and produces a structured security review in under 3 minutes, automatically on every pull request. Built for the complexity of real codebases, PRFlow uses semantic codebase memory to understand cross-repo dependencies and internal patterns before reading the PR. It extracts the right context for the LLM, including the changed function and its cross-file dependencies, instead of sending only the diff or the whole file. Its security-first review focuses on issues like XSS, SSRF, SQL injection, auth bypass, and race conditions by tracing how code flows across files. PRFlow reads the whole PR once and produces a complete structured review with a score, walkthrough, issues by file, severity, strengths, and code fix suggestions directly as inline GitHub PR comments. It supports conversational follow-up inside the PR thread.Starting Price: Free -
25
Parsebridge
Parsebridge
Product information: Parsebridge is a PDF parsing API that transforms PDFs into clean, structured Markdown. It extracts text, tables, and data from PDF documents with a powerful API built for developers who need reliable document parsing at scale. Complex PDFs, tables, multi-column layouts, nested structures, and scanned pages are handled in one API call, turning the hard parts that usually break other parsers into Markdown you can actually use. Merged cells, nested headers, and complex layouts are parsed correctly instead of coming back garbled. Parsebridge supports live testing by pasting a PDF URL or uploading a PDF to the preview page-one Markdown without an account. It currently supports PDF files only, focusing on extraction quality for PDF documents, with files up to 100MB supported. Under the hood, Parsebridge uses Docling, an open source parser known for table extraction and layout preservation, while the platform handles infrastructure, OCR, scaling, and the API layer on top.Starting Price: $17 per month -
26
BrowserQL
Browserless
BrowserQL is a dedicated scraping language, browser automation tool, and infrastructure built to bypass bot detection systems with minimal automation fingerprints. It includes built-in anti-detection with zero configuration, helping users bypass Cloudflare, Datadome, and other bot detection services without manual plugins or setup. BrowserQL can automatically click common CAPTCHA challenges, including those nested in iframes and shadow DOMs, while using auto-humanized clicking, scrolling, typing patterns, hidden debugger protocol, automatic fingerprint evasion, and residential proxy integration to appear more like a real browser. Unlike DIY Playwright setups that require stealth plugins, manual mouse or keyboard simulation, proxy rotation, and constant cat-and-mouse updates, BrowserQL is streamlined to minimize traces left by automation libraries.Starting Price: $25 per month -
27
Exmergo
Exmergo
Exmergo Viz is the Dashboard AI Agent that turns messy data into reliable dashboards in minutes, not weeks. Users can upload or connect datasets, explore them with AI, and generate interactive visualizations from one workspace. It supports structured files such as CSV and Excel, live data connectors, and a centralized Data Hub that lets teams reuse the same data across multiple dashboards and analyses with full traceability. Instead of writing SQL queries, Python scripts, or building charts manually, users ask questions in natural language, request rankings or comparisons, and let Exmergo’s AI analyze datasets in real time to deliver clear, contextual insights. Exmergo Viz creates rich interactive charts, analytical views, built-in analysis, and actionable insights that help teams uncover trends, compare metrics, and share findings faster.Starting Price: $19 per month -
28
InstaVM
InstaVM
InstaVM is a production sandbox and cloud built for AI agents, giving agents instant computers with runtime, storage, networking, secrets, and policy. It goes beyond basic sandboxes by running untrusted code inside hardware-isolated real VMs rather than containers, helping teams give AI agents secure execution environments with full Linux filesystems, networking, package management, RESTful API access, and persistent state. InstaVM supports snapshots, allowing users to fork any sandbox and rewind any run, while persistent volumes keep state beyond each execution. Egress control lets teams allowlist what calls home, secrets injection and Vault help protect sensitive credentials from prompt injections, and public URL deploys can expose any port to the public web. It is built for agent patterns such as code interpreters, deploy agents, deep research agents, AI evaluations, reinforcement learning, computer use, and vibe coding apps.Starting Price: $100 per month -
29
Dock
Dock
Dock is the AI workspace for you, your team, and every agent you run. It gives humans and AI agents the same shared cloud workspace, where everyone can read and write the same state in real time instead of working across scattered chats, files, and one-off outputs. Dock is built around tables with typed columns, rich-text docs, and agents as first-class identities, each with their own API keys, permissions, and audit trail rather than delegated human tokens. Teams can use Dock to plan, research, decide, and ship with humans and AI on the same surface, with use cases across engineering, go-to-market, research, operations, solo work, and agency workflows. Engineering teams can manage sprint planning, spec docs, and incident response; GTM teams can organize content calendars, sales pipelines, and customer success; research teams can track interviews, themes, and competitive intelligence; and operations teams can manage runbooks, recruiting, compliance, and onboarding.Starting Price: $19 per month -
30
ESMC
Biohub
ESMC is the latest in the ESM family of protein language models, establishing a new frontier in representation learning for protein biology. Trained on billions of evolutionary sequences, it learns representations that reflect a mechanistic reduction of protein structure and function. The model is built on a transformer architecture, supports sequences as its core modality, and is trained on up to 6 billion proteins. ESMC is designed for protein science research, including structure prediction, function annotation, protein design, and understanding evolutionary relationships between proteins. It can generate novel proteins from partial sequence, structure, or functional constraints, helping researchers explore new possibilities in protein design and biological discovery. The Biohub Platform provides access to ESMC through the API and the ESM Python package, with quickstart resources for installing the package, creating an API key, connecting to the platform.Starting Price: Free -
31
ESMFold2
Biohub
ESMFold2 is the successor to ESMFold, setting a new state of the art for single-sequence structure prediction and enabling the generation of new functional proteins through searching the ESMC model’s latent space. The model predicts high-resolution, all-atom 3D structures of biomolecular complexes directly from sequence, with optional multiple sequence alignment input for enhanced accuracy on challenging targets. It is designed for structure prediction using sequence and structure modalities, with ESM representations powering a series of looped folding layers and a diffusion model projecting pairwise representations to atomic-resolution predictions. ESMFold2 predicts protein structures directly from amino acid sequences and outputs comprehensive structural information, including all-atom coordinates for backbone and side chains, confidence metrics, and optional distogram predictions for detailed structural analysis.Starting Price: Free -
32
OrcaRouter
OrcaRouter
OrcaRouter is an OpenAI-compatible AI model router that sends each prompt to the right model across OpenAI, Anthropic, Gemini, DeepSeek, Qwen, Kimi, and 200+ frontier and open source models. It is built to preserve frontier answer quality while reducing AI inference spend by grading every prompt and routing hard reasoning to frontier models and routine work to lower-cost open source models. The routing is quality-graded, never a blind, cheap-model swap, and each request shows the difficulty grade, selected model, provider, and cost so routes are visible, auditable, and reproducible. Developers can switch by changing the API base URL, while existing SDKs, model names, and streaming behavior continue to work as before. OrcaRouter supports automatic failover, so if a provider goes down mid-stream, traffic can switch transparently, and the application avoids user-facing errors. It also includes API key management with spend caps, model allowlists, rate limits, budget enforcement, and more.Starting Price: $29 per month -
33
AG2
AG2
AG2 is the open source AgentOS for building production-ready AI agents and multi-agent systems in minutes, not months. Formerly AutoGen, it provides an open source Python framework for building, orchestrating, and scaling AI agents that can collaborate through shared context, use tools, execute workflows, and support both autonomous and human-in-the-loop patterns. AG2 is designed for developers who want to build systems, not prompts, with simple and intuitive syntax, built-in conversation patterns, and a flexible platform for multi-agent automation. Agents in AG2 can extend their capabilities with tools, allowing them to interact with external systems, fetch real-time data, execute code, search the web, process documents, and complete complex tasks beyond a model’s internal knowledge. It supports many LLM providers and local models, including OpenAI-compatible endpoints, Anthropic Claude, Gemini through Vertex AI, DeepSeek, and LM Studio.Starting Price: Free -
34
Agent Client Protocol (ACP)
Agent Client Protocol (ACP)
The Agent Client Protocol (ACP) standardizes communication between code editors, IDEs, and coding agents, making agent-editor interoperability the default instead of requiring custom integrations for every possible combination. It provides a standard interface for communication between AI agents and client applications, with a flexible, extensible, and platform-agnostic architecture designed for both local and remote scenarios. ACP addresses integration overhead, limited compatibility, and developer lock-in by allowing agents that implement the protocol to work with any compatible editor, while editors that support ACP gain access to the broader ecosystem of ACP-compatible agents. Similar in spirit to how the Language Server Protocol standardized language server integration, ACP decouples agents and editors so both sides can innovate independently while developers choose the best tools for their workflow.Starting Price: Free -
35
LocalStack
LocalStack
LocalStack is a cloud development platform that lets teams emulate cloud services across development, testing, and CI environments, so they can build against real APIs, iterate faster, and stay local. It provides a local cloud emulator that runs in a single container on a laptop or in a CI environment, allowing developers to run AWS applications and Lambdas without connecting to a remote cloud provider. LocalStack replicates an application’s production environment on local infrastructure, helping teams build for AWS faster and with more confidence. It is designed for testing complex CDK applications, validating Terraform configurations, learning AWS services, debugging cloud workflows, running integration tests, and simplifying the development loop. Developers can spin up fully functional local environments that mirror real cloud behavior, including AWS services and Snowflake, without provisioning real cloud infrastructure.Starting Price: $39 per month -
36
rawctx
rawctx
rawctx is an AI answer evidence layer for teams shipping customer-facing AI assistants, copilots, and agents. It records each answer with the approved meaning reference, source/context references, model-run metadata, trace IDs, correction history, and exportable proof bundles. Teams can audit why an AI answer was shown, which evidence and business definition it used, what changed after review, and whether trust proof status is anchored, pending, or local-only. rawctx supports answer audit logs, JSON/CSV/proof exports, source_ref evidence binding, and public or private verification workflows for high-stakes support, sales, finance, legal, and operations use cases.Starting Price: $9.99/1000logs -
37
Graphify
Graphify
Graphify is an open source knowledge graph engine that turns any input, including code, docs, papers, meetings, images, browser tabs, and commits, into one traversable graph with complete recall. It is built as persistent memory for AI coding assistants, giving tools like Claude Code, Codex, OpenCode, Cursor, Gemini CLI, GitHub Copilot CLI, Aider, Factory Droid, Kimi Code, Kiro, Pi, and Google Antigravity a queryable understanding of a project instead of making them repeatedly grep through files. Users can point Graphify at any directory, and it builds an initial corpus through AST extraction, semantic analysis, and Leiden clustering, transforming an entire codebase or document corpus into a graph in one pass. Unlike RAG pipelines that re-embed everything on every change, Graphify maintains a living graph that updates only affected nodes and edges when files change, allowing the rest of the corpus to stay intact even at enterprise scale.Starting Price: Free -
38
Hindsight
Vectorize
Hindsight is an agent memory system built to create smarter AI agents that learn over time instead of starting every conversation from zero. Most agent memory systems focus on recalling conversation history, but Hindsight is focused on making agents learn, not just remember. It gives AI agents persistent long-term memory using biomimetic data structures, helping them retain facts, recall relevant context, and reflect on experience as part of reasoning. Hindsight is designed for agents that need to understand who a user is, what has been discussed, what preferences have emerged, what decisions were made, and how behavior should adapt across sessions. It provides three core operations: retain, recall, and reflect. Retain stores new information, recall retrieves the right memories when needed, and reflect helps agents synthesize observations, form mental models, and learn from prior interactions.Starting Price: Free -
39
Pipecat
Pipecat
Pipecat is an open source framework and ecosystem for building real-time voice and multimodal conversational AI agents. It gives developers everything they need to create, deploy, and scale AI applications that can see, hear, and speak, while orchestrating audio, video, AI services, transports, and conversation pipelines with ultra-low latency. The core Pipecat framework is a Python-based system for building voice and multimodal AI pipelines, helping teams connect components such as speech-to-text, LLMs, text-to-speech, vision, video, transports, and business logic without manually wiring every service from scratch. Pipecat is designed to be vendor-neutral and composable, supporting more than 100 AI services so developers can choose the models and providers that fit each use case. Its ecosystem includes Pipecat Subagents for coordinating specialized agents with handoff, task dispatch, and distributed deployment.Starting Price: Free -
40
Vision Agents
Stream
Vision Agents is an open source Python framework for building low-latency voice and video AI agents with any model. It lets developers plug in LLM, speech, and vision models from more than 25 providers and ship real-time agents for telehealth, voice support, live coaching, video analysis, interactive avatars, security monitoring, sports commentary, and other multimodal applications. It is designed to help teams build agents that can listen, speak, see, process media, call tools, and respond in real time while running on Stream’s global edge network with sub-500ms latency. Developers can build a first agent in minutes, using a small Python setup with Gemini Realtime, OpenAI, Deepgram, ElevenLabs, Stream, or other supported providers. Vision Agents supports both real-time speech-to-speech models and custom STT/LLM/TTS pipelines, giving teams either the fastest path to a working voice agent or full control over speech recognition, language reasoning, text-to-speech, etc.Starting Price: Free -
41
Docling
Docling
Docling is an easy-to-use, self-contained, MIT-licensed open source toolkit for converting messy documents into structured data and simplifying downstream document and AI processing. It can parse many popular document formats into a unified and richly structured Docling Document, including PDF, DOCX, PPTX, XLSX, HTML, Markdown, AsciiDoc, CSV, images, audio, and scanned pages through an OCR engine of the user’s choice. Docling detects tables, formulas, reading order, chunks, bounding boxes, page headers and footers, pictures, captions, code, list items, paragraphs, cells, and document structure, making extracted content easier to process, search, and ingest into AI, RAG, and agentic systems. It can export parsed documents to JSON, text, Markdown, HTML, and Doctags, giving developers flexible outputs for pipelines and applications. Docling stores and traverses components according to reading order, partitions documents into bite-sized contiguous text chunks.Starting Price: Free -
42
Proxya
Proxya
Proxya is a premium proxy service provider that offers residential, ISP, and datacenter proxies for businesses and individuals that require reliable online connectivity and anonymity. The platform provides access to proxy networks across more than 195 countries, allowing users to target specific locations at the country, state, or city level. Its residential proxies use real device IP addresses, while ISP proxies combine residential trust with datacenter-level speed and performance. Proxya’s datacenter proxies are designed for high-volume tasks and deliver fast, stable connections with unlimited traffic options. The platform supports use cases such as web scraping, SEO monitoring, ad verification, market research, social media management, and price comparison. With instant activation, API integration, 24/7 customer support, transparent pricing, and a 99.9% uptime commitment, Proxya helps users deploy proxy solutions quickly and efficiently.Starting Price: $1 -
43
Yade
Yade
Yade is an extensible open source framework for discrete numerical models, focused on the Discrete Element Method. Its computation parts are written in C++ using a flexible object model that allows independent implementation of new algorithms and interfaces, while Python is used for rapid and concise scene construction, simulation control, postprocessing, and debugging. Yade is designed for researchers and engineers who need to create, run, inspect, modify, and extend particle-based simulations through scripts, interactive commands, graphical tools, and reusable simulation components. Simulations can be built from specialized generators or constructed directly with Python scripts, giving users flexibility for developing custom models, importing geometries, reusing code, and controlling the full simulation loop. It represents each simulation as a scene containing bodies, interactions, and resultant forces, with bodies defined by geometry, material properties, state variables, etc.Starting Price: Free -
44
MFiX
National Energy Technology Laboratory
MFiX, or Multiphase Flow with Interphase eXchanges, is an open source multiphase flow solver and NETL’s flagship suite of computational fluid dynamics tool for modeling reacting multiphase flows. It has become a standard for comparing, implementing, and evaluating multiphase flow constitutive models, and has been applied to a diverse range of multiphase flow devices and industrial systems. MFiX provides multiple modeling approaches, including a Two-Fluid Model, Discrete Element Model, Coarse-Grained Particle DEM, Superquadric Particle DEM, Glued-Sphere Particle DEM, Particle-in-Cell model, hybrid methods, and a single-phase solver for pure granular flows. These models can be used to simulate gasifiers, circulating fluidized bed combustors, fluidized beds, fluid catalytic crackers, chemical looping combustion systems, and other particle-fluid systems involving hydrodynamics, heat transfer, species transport, and chemical reactions.Starting Price: Free -
45
ESPResSo
ESPResSo
ESPResSo, the Extensible Simulation Package for Research on Soft Matter, is a highly versatile open source simulation package for performing and analyzing scientific molecular dynamics and Monte Carlo many-particle simulations. It is designed as a universal tool for simulating a variety of soft matter systems, especially coarse-grained atomistic or bead-spring models used in physics, chemistry, molecular biology, and process engineering. ESPResSo can be used to simulate polymers, liquid crystals, colloids, polyelectrolytes, ferrofluids, gels, biological systems, DNA, lipid membranes, bacterial motion, and super-capacitors. In coarse-grained models, a group of atoms or molecules is treated as a single bead, allowing researchers to investigate larger time and length scales than would be practical with fully atomistic simulations. ESPResSo supports classical molecular dynamics simulations in different statistical ensembles.Starting Price: Free -
46
Rocket Open AppDev for Z
Rocket Software
Rocket Open AppDev for Z helps organizations modernize mainframe DevOps with secure open-source software, bringing applications to market faster, at lower cost, and with less risk. It is much more than a collection of open source ports for z/OS: it combines years of investment in automation infrastructure, packaging and delivery options, and an experienced support team. It brings together the high security mainframe customers demand with an easy user experience for developers and admins. Trusted by leading banks, insurance companies, and government agencies, Open AppDev for Z provides open-source languages and tools for z/OS while checking deliverables for vulnerabilities and following proper licensing requirements. Its products are continuously kept up to date against the NIST National Vulnerability Database, with open-source ports delivered and maintained through a public conda channel, private conda channel, on-premises conda file channel, or SMP/E.Starting Price: Free -
47
Manufact
Manufact
Manufact is a platform to build and deploy MCP apps and servers, giving teams a fast path to the ChatGPT Apps Store, Claude Connectors, and every surface where users and agents already work. The mcp-use SDK is the full-stack MCP framework to develop MCP apps for ChatGPT and Claude, as well as MCP servers for AI agents. Manufact covers every step of the MCP lifecycle with no extra tools: build from an SDK, a skill, or a vibe; deploy with one push; publish with marketplace checklists and generated submission assets; iterate with Cloud Inspector; and monitor with analytics, session replay, traces, error rates, and alerts. Teams can scaffold with the MCP-use SDK, install a skill into a coding agent, describe an app and watch it scaffold, or drop in an existing MCP server unchanged. Manufact Cloud connects to a repo once, then every push auto-deploys, with preview URLs for pull requests, custom domains, and SSL handled.Starting Price: $25 per month -
48
Dokploy
Dokploy
Dokploy is an open source, self-hostable Platform as a Service that simplifies the deployment and management of applications and databases. Built for developers seeking control and flexibility, it gives teams a straightforward way to deploy apps on their own infrastructure with full control, no vendor lock-in, and none of the Kubernetes complexity. Dokploy can be installed with a single command and used to deploy projects in minutes, centralizing control of applications, databases, logs, monitoring, backups, and multi-server environments in one clean interface. It supports single services and multi-service apps, with native Docker Compose support, Git-based deployments, container registry deployments, custom Docker images, Dockerfiles, Nixpacks, and Buildpacks, so teams can choose the build strategy that fits each project without reworking their pipeline.Starting Price: $4.50 per month -
49
Azure DocumentDB
Microsoft
Azure DocumentDB is an open source, MongoDB-compatible document database service built to help teams build AI-driven apps, migrate MongoDB workloads, and standardize on a portable document database engine. It supports hybrid and multicloud architectures with enterprise-grade performance, availability, security, management, and easy Azure AI integration. Built on DocumentDB, the open-source engine hosted at the Linux Foundation, Azure DocumentDB gives developers transparency, community-driven innovation, and freedom from restrictive licenses while supporting familiar MongoDB skills, drivers, tools, APIs, BSON and JSON documents, and popular languages such as Node.js, Python, Java, and .NET. Teams can build and test MongoDB-compatible apps in their own environment, including local, on-premises, and other clouds, then deploy to Azure DocumentDB for enterprise-grade scale and management.Starting Price: $13.943 per month -
50
Ornith-1.0
DeepReinforce
Ornith-1.0 is a self-improving family of models built specially for agentic coding tasks. It spans the full spectrum from compact 9B Dense models suitable for edge device deployment to 397B MoE frontier-scale models optimized for maximum performance, with variants including 9B Dense, 31B Dense, 35B MoE, and 397B MoE. Built on top of pretrained Gemma 4 and Qwen 3.5, Ornith-1.0 achieves state-of-the-art performance among open-source models of comparable size on coding benchmarks. Its key innovation is a self-improving training framework that learns to generate both solution rollouts and the task-specific scaffolds that guide those rollouts. Instead of relying on fixed, human-designed harnesses, Ornith-1.0 treats the scaffold as a learnable object that co-evolves with the policy, allowing the model to jointly optimize the orchestration and the final solution.Starting Price: Free
