Repository History
Explore all analyzed open source repositories
OGAD: Private, On-Device AI with an OpenAI-Compatible Local Gateway
OGAD (Off Grid AI Desktop) is an open-source, AGPL-licensed application for private, on-device AI. It enables users to run various open models, including text, vision, image, and voice, entirely locally through a single OpenAI-compatible gateway. This ensures complete data privacy with no cloud dependencies, accounts, or API keys.
agent.cpp: Building Local LLM Agents with C++ and llama.cpp
agent.cpp provides essential building blocks for developing local AI agents using C++. It leverages llama.cpp to enable efficient execution of small language models directly on your hardware. This library offers a modular approach with features like agent loops, callbacks, tools, and grammar-constrained output, making it ideal for creating custom, privacy-focused agent solutions.
Wasm Agents Blueprint: Run Python AI Agents in Your Browser with WebAssembly
Wasm Agents Blueprint is an innovative project from Mozilla AI that allows you to run Python-based AI agents directly in your web browser using WebAssembly (Wasm) and Pyodide. It bridges the gap between powerful Python AI frameworks, like the OpenAI Agents SDK, and browser-based applications. This blueprint eliminates the need for complex server setups or Docker containers, offering a streamlined way to experience AI agents.
Agent Factory: Generate AI Agents with Natural Language Descriptions
Agent Factory, developed by Mozilla-AI, is a powerful tool designed to generate AI agents and workflows. It allows users to describe tasks in natural language, which it then transforms into executable Python code for agentic workflows. Leveraging the Model Context Protocol (MCP) and the any-agent library, it simplifies the creation of complex AI solutions.
EnvHarness: Dynamically Adapting Environments for Agent Learning
EnvHarness empowers large language models (LLMs) acting as autonomous agents to learn more effectively from interactive environments. It achieves this by wrapping static environments with plug-in components, making them dynamically controllable without altering their internal code. This innovative approach allows environments to target specific agent weaknesses and continuously teach as agents improve, leading to more effective and efficient learning outcomes.
agenttrail: Real-time Observability for Your AI Coding Agents
agenttrail provides a local, open-source observability layer for AI coding agents. It transforms agent plans, tool calls, and file changes from tools like Claude Code, OpenAI Codex, and Cursor into a live, zoomable project map. This allows developers to monitor agent progress and activity in real time, ensuring they know what their agents are doing as it happens.
Magic Context: Unbounded, Self-Managing Memory for AI Coding Agents
Magic Context is a powerful GitHub repository that provides unbounded, self-managing memory for AI coding agents. Acting as the 'hippocampus' for agents, it ensures continuous learning and recall across sessions without disruptive context compaction. This tool, part of CortexKit, allows agents to build lasting project knowledge and maintain context efficiently.
AFT: A Sensorimotor Cortex for Coding Agents with IDE and OS Capabilities
AFT provides coding agents with advanced IDE and OS capabilities, acting as a sensorimotor cortex for perception and action within a codebase. It enhances agent productivity and reduces token usage by offering structured code perception, precise symbol-aware edits, and background task management. Part of the CortexKit family, AFT integrates with platforms like OpenCode and Pi to elevate agent interaction with code.
tunnel-client: Securely Connect Private MCP Servers to OpenAI Services
The `tunnel-client` is an OpenAI-developed client that enables secure connections between private or localhost Model Context Protocol (MCP) servers and OpenAI services like ChatGPT, Codex, and AgentKit. It allows developers to integrate their internal MCP servers without exposing them to the public internet, ensuring enhanced security and operational control. This tool is ideal for scenarios requiring secure access from private networks to OpenAI's powerful AI models.
github-tools: Seamless GitHub API Integration for Vercel AI SDK Agents
github-tools offers a powerful collection of GitHub tools and agents specifically designed for the Vercel AI SDK. This project enables developers to effortlessly wrap GitHub's API as AI SDK tools, making them ready to plug into any AI agent. It significantly simplifies the creation of intelligent applications that interact with GitHub.
deja-vu: Retroactive Memory for AI Coding Agents
deja-vu is a powerful local-first tool that provides retroactive memory for AI coding agents, indexing past coding sessions from various agents, even those from before installation. This Go binary allows agents to recall relevant information without needing an LLM or embeddings by default. It enhances agent performance by providing context at the point of action, preventing repeated mistakes and improving efficiency.
ArcReel: Open-Source AI Video Production Workspace for Stories and Scripts
ArcReel is an open-source, self-hosted AI video production workspace designed to transform novels, screenplays, or product assets into short videos. It offers a comprehensive pipeline for content analysis, asset management, storyboarding, and video generation, ensuring visual continuity and cost tracking. Users can control the production process and export editable drafts for further refinement.