Search Results for "agents" - Page 7
Sort By:
Showing 512 open source projects for "agents"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
Secure File Transfer for Windows with Cerberus by RedwoodCerberus supports unlimited users and connections on a single IP, with built-in encryption, 2FA, and a browser-based web client — all deployable in under 15 minutes with a 25-day free trial.
-
1
Ultravox
Fast multimodal LLM for real-time voice interaction and AI apps
...Internally, it leverages pretrained language models and speech encoders, with a multimodal adapter that integrates both modalities for inference and training. Ultravox is optimized for low latency, achieving fast response times suitable for interactive voice agents and real-time applications. It supports use cases such as conversational AI agents, speech-to-speech translation, and analysis of spoken audio content. Ultravox also includes tooling and configuration systems for training, evaluation, and dataset integration. -
2
Windows-MCP
MCP server enabling AI agents to control and automate Windows OS
Windows-MCP is a lightweight open source project designed to connect AI agents with the Windows operating system through a Model Context Protocol server. It acts as a bridge that allows large language models to directly interact with desktop environments, enabling automated control over applications, files, and system interfaces. Windows-MCP provides capabilities such as file navigation, application management, UI interaction, and QA testing workflows, making it suitable for building autonomous desktop agents. ... -
3
cognee
Deterministic LLMs Outputs for AI Applications and AI Agents
Cognee implements scalable, modular data pipelines that allow for creating the LLM-enriched data layer using graph and vector stores. Cognee acts a semantic memory layer, unveiling hidden connections within your data and infusing it with your company's language and principles. This self-optimizing process ensures ultra-relevant, personalized, and contextually aware LLM retrievals. Any kind of data works; unstructured text or raw media files, PDFs, tables, presentations, JSON files, and so... -
4
CLI-Anything
Making ALL Software Agent-Native
CLI-Anything is a framework designed to transform traditional software applications into agent-native command-line interfaces that can be directly controlled by AI systems. It is built on the idea that the command-line interface is the most universal, structured, and composable interface for both humans and AI agents, enabling deterministic and predictable execution of workflows. The system provides a methodology and tooling for generating CLI wrappers around existing applications, allowing them to be controlled programmatically using natural language instructions interpreted by AI agents. It integrates with multiple AI platforms such as Claude Code, OpenClaw, Codex, and GitHub Copilot CLI, enabling cross-platform compatibility and flexibility. ... -
Stop Storing Third-Party Tokens in Your DatabaseRolling your own OAuth token storage can be a security liability. Token Vault securely stores access and refresh tokens from federated providers and handles exchange and renewal automatically. Connected accounts, refresh exchange, and privileged worker flows included.
-
5
Director
AI video agents framework for next-gen video interactions
Director is a video database management system designed to organize, search, and retrieve large collections of video content efficiently. -
6
Diplomacy Cicero
Code for Cicero, an AI agent that plays the game of Diplomacy
...The repository includes training code, model checkpoints, and infrastructure for both language modelling (via the ParlAI framework) and reinforcement learning for strategy agents. It supports two variants: Cicero (which handles full “press” negotiation) and Diplodocus (a variant focused on no-press diplomacy) as described in the README. The codebase is implemented primarily in Python with performance-critical components in C++ (via pybind11 bindings) and is configured to run in a high‐GPU cluster environment. ... -
7
Google Antigravity SDK
Python library for building agents that leverages Google Antigravity
...The package relies on a compiled runtime binary distributed through platform-specific PyPI wheels, so installation from PyPI is required for normal use. Its main value is giving developers a structured Python framework for creating local, tool-using, multimodal, policy-controlled AI agents. -
8
Khazix Skills
Digital Life Kazik Open Source AI Skills Collection
...The system emphasizes lifecycle management by embedding versioning, traceability, and metadata directly into generated skill files, allowing future updates and synchronization with the original repository. It also generates wrapper scripts that enable AI agents to interact with the underlying repository functionality without requiring deep manual integration. By enforcing a consistent schema, the project ensures interoperability between skills and simplifies deployment across environments. This makes it especially useful for teams building modular AI agents that rely on external tools or open-source repositories. -
9
ACI.dev
Open platform connecting AI agents to tools via unified MCP server
ACI is an open source platform designed to enable AI agents to interact with external tools through a unified and structured interface. It focuses on simplifying tool integration by connecting hundreds of pre-built services into agentic environments, allowing developers to avoid building custom API clients and authentication flows for each service. ACI provides intent-aware tool access, meaning agents can dynamically discover and use tools based on context rather than rigid configurations. ... -
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
10
AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
AgentBench is an open-source benchmark designed to evaluate the capabilities of large language models when used as autonomous agents. Unlike traditional language model benchmarks that focus on static text tasks, AgentBench measures how models perform in interactive environments that require planning, reasoning, and decision-making. The benchmark includes multiple environments that simulate realistic scenarios such as web interaction, database querying, and problem solving tasks. ... -
11
CUDA Agent
Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
CUDA Agent is a research-driven agentic reinforcement learning system designed to automatically generate and optimize high-performance CUDA kernels for GPU workloads. The project addresses the long-standing challenge that efficient CUDA programming typically requires deep hardware expertise by training an autonomous coding agent capable of iterative improvement through execution feedback. Its architecture combines large-scale data synthesis, a skill-augmented CUDA development environment,... -
12
Self-Operating Computer
A framework to enable multimodal models to operate a computer
The Self-Operating Computer Framework is an innovative system that enables multimodal models to autonomously operate a computer by interpreting the screen and executing mouse and keyboard actions to achieve specified objectives. This framework is compatible with various multimodal models and currently integrates with GPT-4o, o1, Gemini Pro Vision, Claude 3, and LLaVa. Notably, it was the first known project to implement a multimodal model capable of viewing and controlling a computer screen.... -
13
Semantic Router
Superfast AI decision making and processing of multi-modal data
Semantic Router is a superfast decision-making layer for your LLMs and agents. Rather than waiting for slow, unreliable LLM generations to make tool-use or safety decisions, we use the magic of semantic vector space — routing our requests using semantic meaning. Combining LLMs with deterministic rules means we can be confident that our AI systems behave as intended. Cramming agent tools into the limited context window is expensive, slow, and fundamentally limited. -
14
Agent Control
Centralized agent control plane for governing runtime agent behavior
...The repository includes SDKs, a server, telemetry components, examples, and integrations for common agent frameworks. It is especially useful for teams building customer-facing, internal, or enterprise agents that need scalable runtime guardrails. -
15
Continuous Claude v3
Context management for Claude Code. Hooks maintain state via ledgers
...Rather than relying on a single session’s context, Continuous Claude uses mechanisms like ledgers, YAML handoffs, and a memory system to preserve and recall state across multiple sessions, ensuring that learned insights and plans are not lost when context compaction occurs. The project orchestrates many specialized agents and skills—109 skills and 32 agents—so that complex coding tasks can be broken down, analyzed, and executed collaboratively by different components. It also includes a layered code analysis pipeline to reduce token usage and maintain relevant context efficiently. This continuous learning environment enables workflows such as bug fixing, refactoring, planning, and exploratory investigation while minimizing the need to re-explain context manually. -
16
ex-skill
Distill your ex into an AI Skill
ex-skill is an experimental AI tooling project that allows users to transform personal memories, particularly past relationships, into interactive AI “skills” that replicate the communication style, personality, and behavioral patterns of a specific individual. The system works by ingesting various forms of personal data such as chat logs, social media content, photos, and user-provided descriptions, then structuring this information into a layered representation that combines memory and... -
17
AppWorld
World of apps for benchmarking interactive coding agent
AppWorld is a framework developed by Stony Brook University's NLP group to simulate environments for training and evaluating dialogue agents in task-oriented applications. -
18
Potpie
Create custom engineering agents for your codebase
Potpie is an AI-powered data analysis tool that automates the exploration and visualization of datasets, assisting users in uncovering insights without extensive coding. -
19
Agent Behavior Monitoring
The open source post-building layer for agents
Agent Behavior Monitoring is an open-source framework designed to monitor, evaluate, and improve the behavior of AI agents operating in real or simulated environments. The system focuses on agent behavior monitoring by collecting interaction data and analyzing how agents perform across different scenarios and tasks. Developers can use the framework to observe agent actions in both online production environments and offline evaluation settings, making it useful for debugging and performance analysis. ... -
20
E2B Desktop Sandbox
E2B Desktop Sandbox for LLMs. E2B Sandbox
...Within a sandbox, developers can launch applications like browsers, editors, or other software that an AI agent may need to interact with. This approach is particularly useful for building AI agents capable of interacting with graphical environments or performing tasks such as browsing, testing software, or automating workflows. -
21
ControlFlow
Take control of your AI agents
...The framework provides a structured approach for building AI systems by breaking complex tasks into smaller units called tasks that can be assigned to specialized AI agents. Developers can combine these tasks into flows that define how work is executed, enabling the creation of multi-step reasoning pipelines and collaborative agent systems. ControlFlow focuses on maintaining transparency and control in AI applications by providing explicit workflow structures instead of opaque chains of prompts. The system integrates with common LLM providers and allows developers to create workflows that blend traditional software logic with AI-driven reasoning. ... -
22
OpenAI Agent Skills
Skills Catalog for Codex
OpenAI Agent Skills is an open-source repository that serves as a broad catalog of agent skills designed to extend the capabilities of OpenAI Codex and other AI coding agents. It organizes reusable, task-specific workflows, instructions, scripts, and resources into modular skill folders so that an AI agent can reliably perform complex tasks without repeated custom prompting, making agent behavior more predictable and composable. Each skill is defined with clear metadata and instructions organizing how an AI assistant should complete specific tasks ranging from project management to code generation and documentation assistance. ... -
23
AIBuildAI
An AI agent that automatically builds AI models
...The project explores recursive AI development, where models are used not only as tools but as builders capable of constructing other AI systems, workflows, or components. It provides a structured environment for orchestrating agents that can plan, execute, and refine tasks such as code generation, system design, and iterative improvement loops. The framework is designed to support experimentation with self-improving AI pipelines, allowing developers to test concepts like automated architecture search or adaptive system evolution. It integrates multiple components including prompt management, execution control, and feedback loops to ensure that generated outputs can be evaluated and improved over time. -
24
Hermes Web UI
The best way to use Hermes Agent from the web or from your phone
Hermes WebUI is a browser-based interface for interacting with the Hermes autonomous agent, providing full feature parity with its command-line experience. It offers a clean, multi-panel layout that includes chat interaction, session management, and workspace file browsing. The interface allows users to manage agent sessions, configure models, and interact with persistent memory systems directly from a web environment. It is built using simple technologies like Python and vanilla JavaScript,... -
25
Letta
Letta (formerly MemGPT) is a framework for creating LLM services
Letta is an AI-powered task automation framework designed to handle workflow automation, natural language commands, and AI-driven decision-making.
