Search Results for "context" - Page 19
Sort By:
Showing 785 open source projects for "context"
View related business solutions-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
1
AgentScope Java
Agent-Oriented Programming for Building LLM Applications
...The framework includes runtime controls such as safe interruption and graceful cancellation to manage agent execution robustly in production environments. It also supports human-in-the-loop intervention, allowing developers or users to inject guidance at any point during reasoning while preserving state and tool context. Built with enterprise needs in mind, AgentScope Java integrates into traditional Java stacks and provides structured abstractions for memory, workflows, and tool invocation. -
2
DeepSeek-OCR
Contexts Optical Compression
DeepSeek-OCR is an open-source optical character recognition solution built as part of the broader DeepSeek AI vision-language ecosystem. It is designed to extract text from images, PDFs, and scanned documents, and integrates with multimodal capabilities that understand layout, context, and visual elements beyond raw character recognition. The system treats OCR not simply as “read the text” but as “understand what the text is doing in the image”—for example distinguishing captions from body text, interpreting tables, or recognizing handwritten versus printed words. It supports local deployment, enabling organizations concerned about privacy or latency to run the pipeline on-premises rather than send sensitive documents to third-party cloud services. ... -
3
TrustClaw
A self-hostable personal AI agent with vector memory
...It is built for users who want their own AI agent rather than a fully hosted platform, making it easier to run, inspect, and adapt the system for personal or technical needs. The project uses vector memory so the assistant can retain and retrieve useful context across interactions. It also integrates Composio tools, giving the agent access to third-party actions and services through a broader tool ecosystem. Telegram support makes the assistant reachable from a familiar messaging interface instead of only through a terminal or web app. Overall, it is aimed at developers and power users who want a customizable, always-available personal assistant with memory, tools, and self-hosted control. -
4
Hermes Web UI
The best way to use Hermes Agent from the web or from your phone
...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, avoiding complex frontend frameworks. The UI supports real-time interaction, context tracking, and visualization of token usage. It connects to a self-hosted agent that continuously learns and evolves over time. The project emphasizes usability, accessibility, and seamless integration with existing workflows. -
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.
-
5
HolyClaude
AI coding workstation: Claude Code + web UI + 5 AI CLIs + headless
...The project centers around improving how developers interact with AI agents, enabling more efficient code generation, debugging, and task execution through optimized prompt engineering. It includes predefined templates and interaction patterns that guide the AI toward producing more accurate and context-aware responses. HolyClaude emphasizes productivity by reducing friction in iterative development cycles, allowing users to refine outputs quickly without repeatedly crafting instructions from scratch. The toolkit is modular in nature, enabling developers to adapt it to different coding scenarios or integrate it into their existing workflows. ... -
6
Code-Graph-RAG
The ultimate RAG for your monorepo
...It uses Tree-sitter to parse source code into abstract syntax trees, extracting relationships between functions, classes, and modules to build a graph-based representation of the entire codebase. This structured approach enables more accurate and context-aware querying compared to traditional text-based search methods, allowing users to ask natural language questions about code structure and functionality. The system integrates with graph databases such as Memgraph to store and manage relationships, enabling efficient querying and visualization of complex dependencies. It also supports AI-driven query translation, converting natural language into graph queries for deeper analysis and interaction. -
7
Godot MCP
MCP server for interfacing with Godot game engine
Godot MCP is a Model Context Protocol server that enables AI assistants to directly interact with the Godot game engine, allowing programmatic control over game development workflows through natural language or agent-driven commands. It acts as a bridge between AI systems and the Godot editor, providing capabilities such as launching projects, running games in debug mode, and capturing runtime output for analysis. -
8
HyperAgent
AI Browser Automation
HyperAgent is an open-source browser automation framework that combines large language models with modern browser scripting tools to create intelligent web automation agents. Built on top of Playwright, the framework allows developers to automate complex browser interactions using natural language commands rather than fragile selectors or hard-coded scripts. Instead of manually writing logic for clicking elements, extracting data, or navigating web pages, developers can instruct the agent in... -
9
Neuron AI
The PHP Agentic Framework to build production-ready AI driven apps
Neuron AI is a PHP agentic framework for building production-ready AI applications that connect models, memory, vector databases, and tools into working agents. It is designed for developers who want to create systems such as RAG pipelines, multi-agent workflows, and business process automations without having to hand-build every integration from scratch. The framework provides an Agent class that can be extended to inherit core capabilities like memory, tools, function calling, and... -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
Poco Claw
A more beautiful and easier-to-use alternative to OpenClaw
Poco Claw is an AI agent platform designed as a more user-friendly and visually polished alternative to traditional OpenClaw implementations. It focuses on improving usability by providing a modern web interface combined with enhanced interaction capabilities such as built-in messaging and project organization tools. The system operates on a sandboxed runtime, ensuring that tasks executed by the agent are isolated from the host environment, which improves security and reliability. It extends... -
11
canvas-editor
Canvas-based WYSIWYG rich text editor with advanced layout tools
...It includes support for page-based layouts with headers, footers, pagination, and print-ready output, including PDF generation. It also provides interactive components such as form controls and context menus, making it suitable for building complex document editing systems. -
12
ClawRouter
Smart LLM router
...It provides a programmable router abstraction that can handle complex traffic patterns, enabling dynamic message forwarding, load balancing, and custom routing logic based on content, context, or policy rules. Because distributed AI systems often involve many services, agents, and runtime components interacting with each other and with external APIs, ClawRouter helps ensure that communication paths remain clear, efficient, and adaptable as systems scale. The framework supports plugin-based extensions so developers can define custom protocols, transformation hooks, and monitoring handlers without modifying core routing logic. ... -
13
Corsair
Your Agent's Integration Layer
...A permission system can allow, require approval for, or block read, write, and destructive operations. Credentials are resolved internally and can be stored with envelope encryption rather than passed into model context. Multi-tenant mode isolates each tenant's credentials, data, and permission evaluation. Plugins can also provide signature-verified webhooks through a shared endpoint. Corsair is designed for production agent systems that need OAuth, scoped authorization, human approval, and centralized integration control. -
14
Llama Cookbook
Solve end to end problems using Llama model family
The Llama Cookbook is the official Meta LLaMA guide for inference, fine‑tuning, RAG, and multi-step use-cases. It offers recipes, code samples, and integration examples across provider platforms (WhatsApp, SQL, long context workflows), enabling developers to quickly harness LLaMA models -
15
Reins
Ollama client that simplifies experimenting with LLMs
...It provides a highly customizable chat interface where users can configure system prompts, switch models dynamically, and adjust inference parameters such as temperature, token limits, and context size on a per-conversation basis. The application is built to run across platforms including mobile and desktop environments, making it accessible for a wide range of users who want consistent control over their AI workflows. It also includes features for editing and regenerating messages, enabling iterative refinement of outputs without restarting conversations. ... -
16
CodexPro
Use ChatGPT Developer Mode as a local coding agent for your repo
CodexPro is a local MCP bridge that lets ChatGPT Developer Mode work inside a specific code repository. It starts a local server for the current workspace so ChatGPT can read files, search code, apply scoped edits, run guarded shell checks, and review changes. The project is designed around local control rather than hosting code or proxying model access through a third-party service. It supports setup, start, doctor, settings, handoff, and pro modes for different levels of agent involvement.... -
17
Codebuff
Generate code from the terminal!
...Instead of relying on a single model, it orchestrates multiple specialized agents that collaborate to understand, plan, edit, and review code changes. This multi-agent approach enables more accurate edits, better context awareness, and fewer errors across complex projects. Codebuff operates primarily through a CLI, allowing developers to interact with their code directly from the terminal. It also offers an SDK for integrating agent-based coding workflows into applications and development pipelines. With support for multiple AI models and customizable agents, Codebuff provides a flexible and powerful alternative to traditional coding assistants. -
18
kubectl-ai
AI assistant for managing Kubernetes clusters from the terminal
kubectl-ai is an AI-powered command-line assistant designed to help users manage and interact with Kubernetes clusters through natural language queries. It acts as an intelligent interface that interprets user intent and translates it into appropriate Kubernetes operations and commands. By integrating large language models, it enables users to ask questions or request actions in plain language instead of manually crafting complex Kubernetes commands. kubectl-ai runs directly in the terminal... -
19
MemOS
AI memory OS for LLM and Agent systems
...The project explores rethinking system abstractions by tightly coupling computation with memory objects so that programs can operate on large datasets without expensive serialization or context switching. It aims to support advanced workflows like persistent in-memory data structures, crash-resilient state handling, and seamless sharing of data across tasks without copying. By abandoning some of the historical assumptions of Unix-style operating systems, MemOS attempts to unlock new performance and scalability tradeoffs for applications that need high throughput and low latency on memory-intensive workloads. -
20
Beads
A memory upgrade for your coding agent
...Instead of storing plans as unstructured Markdown or ephemeral notes, Beads organizes agent state, task artifacts, and relationships as nodes and edges in a version-controlled graph so that long-horizon projects don’t lose context or coherence as the agent proceeds. This approach helps coding agents — and human collaborators — track which tasks depend on others, what has been done, and where workflows branch or reunify without losing important data. By leveraging Git as the storage backbone, the project ensures that memory is persistent, diffable, and sharable, with the ability to roll back, branch, or merge memory states just like source code. -
21
GitHub Copilot SDK
Multi-platform SDK for integrating GitHub Copilot Agent into apps
...Instead of being limited to editors like VS Code, this SDK lets teams embed Copilot-style code suggestions, natural language assistance, and predictive completions anywhere they see fit—such as internal IDEs, browser extensions, documentation portals, or bespoke tools tailored to specific languages or frameworks. It provides a structured API surface for invoking the Copilot model in context with the surrounding user state, capturing document content, cursor position, and invocation triggers so suggestions are relevant and responsive. The SDK includes helpers for streaming completions, managing rate limits, handling authentication, and integrating with telemetry and analytics pipelines. -
22
Hindsight
Hindsight: Agent Memory That Learns
...Instead of relying solely on vector similarity or basic retrieval techniques, Hindsight organizes information into distinct categories such as facts, experiences, beliefs, and observations, allowing agents to differentiate between raw data and inferred knowledge. The system operates through three core mechanisms—retain, recall, and reflect—which respectively handle storing information, retrieving relevant context, and generating new insights based on accumulated experience. -
23
MindSearch
An LLM-based Multi-agent Framework of Web Search Engine
MindSearch is an AI-powered search engine based on large language models (LLMs) designed for deep semantic search and retrieval. It leverages InternLM's language model to understand complex queries and retrieve highly relevant answers from large datasets. -
24
Guidance
A guidance language for controlling large language models
Guidance is an efficient programming paradigm for steering language models. With Guidance, you can control how output is structured and get high-quality output for your use case—while reducing latency and cost vs. conventional prompting or fine-tuning. It allows users to constrain generation (e.g. with regex and CFGs) as well as to interleave control (conditionals, loops, tool use) and generation seamlessly. -
25
Chronos Forecasting
Pretrained (Language) Models for Probabilistic Time Series Forecasting
...A time series is transformed into a sequence of tokens via scaling and quantization, and a language model is trained on these tokens using the cross-entropy loss. Once trained, probabilistic forecasts are obtained by sampling multiple future trajectories given the historical context. Chronos models have been trained on a large corpus of publicly available time series data, as well as synthetic data generated using Gaussian processes.
