Open-source MCP harness connecting AI assistants to local code and coordinating coding agents.
- Free
Audit Claude Code token usage, diagnose limits, and trace context overhead from local session logs.
FreeOpen-source coding agent orchestration that turns backlog issues into verified, review-ready pull requests.
FreeOpen-source agent skills and a Python service for removing AI provenance marks from owned text and files.
FreeConnect ChatGPT planning and code review to Codex execution through a read-only workspace bridge.
FreeOpen-source terminal agent runtime for research, sandboxed file work, and parallel agent teams.
FreeOpen-source optimization of prompts, code, agent architectures, and configurations using LLM reflection.
FreeRun Qwen Mixture-of-Experts models locally on Macs and iPhones by streaming expert weights from storage.
Freecode-graph-rag indexes multi-language codebases for natural-language search, code editing and analysis.
FreeLocal AI IDE account management with account switching, quota monitoring and parallel application instances.
FreeOpen-source agent orchestration for Claude Code, Codex and MCP clients, with swarms, memory and workflow controls.
FreeAn open-source CLI that lets AI agents control local and cloud iPhones and Android phones.
FreeDesktop account management, API protocol conversion, and request routing for AI services.
FreeOpen-source CLI harnesses that let AI agents work with desktop software, developer tools, and services.
FreeOpen-source PyTorch distributed training and fine-tuning for language and vision-language models
FreeVision tools for text-only models in DeepSeek Harness, including image Q&A, screenshot OCR, and UI restoration.
FreePack repositories into AI-friendly files with token counts, configurable exclusions, and optional code compression.
FreeAn agent skill that turns goals into prompts for builder-critic loops and blind quality comparisons.
FreeOpen-source AI agent for coding, research and parallel multi-model workflows from the command line.
FreeOpen-source GitHub Action for Claude-powered security reviews of pull requests and code changes.
FreeA Durable Object-backed virtual filesystem with pluggable shell, container and JavaScript execution.
FreeOpen-source coding and research agent with persistent Python sessions, subagents, and long-running autonomous workflows.
FreeLocal-first control plane for agent teams, with durable goals, decisions, ownership and evidence across sessions.
FreeOpen-source local LLM inference for Metal, CUDA and ROCm, with a coding agent and HTTP server.
FreeOpen-source terminal coding agent that reads repositories, edits files, and runs commands with cloud or local models.
FreeSwitch between isolated Claude Code accounts on Linux and macOS without logging in again.
FreeOpen-source background coding agents with shared sessions, development sandboxes, and scheduled automations.
FreeOpen-source multi-agent framework for authorized security testing through a browser interface or CLI.
FreeUnofficial Python API, CLI, and agent tools for automating Google Gemini Notebook research and content generation.
FreeOpen-source backend for coding agents with Postgres, authentication, storage, edge functions, and an AI gateway.
FreeOfficial Python library for the OpenAI API with synchronous, asynchronous, streaming, and Realtime support.
FreeOpen-source AI agent swarm for authorized API and web application penetration testing.
Free



































