
REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

CLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally
Open-source agent harness from DeepSeek, built on a plugin architecture

Local MCP server that builds a code knowledge graph for AI coding agents
Runs locally
Desktop environment for running several coding agents in parallel worktrees

Local search engine for AI agents with cited answers over your code and docs
Runs locally
Terminal coding agent in Rust that works with any model and can split tasks across agents

Terminal coding agent with LSP, debugger access, subagents and a native Rust core

Terminal coding agent that talks to OpenAI, Gemini, Ollama and 200-plus other models

Run macOS, Linux and Windows desktops for agents on computers you own

Spec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally
Command-line tool that exposes every Google Workspace API with JSON output for agents

Scanner that checks agent skills for prompt injection, exfiltration and other risks

Run many coding agents in parallel, each on its own branch, with PR and CI feedback loops

Strands toolkit with a ready agent harness, sandbox and evals in Python and TypeScript

Self-evolving engine that lets agents share and reuse learned capabilities

Use ChatGPT on the web to plan and review while Codex executes your coding tasks
Local-first MCP server for messaging and shared work-state between coding agents
Runs locally
Local code search for coding agents that returns only the relevant snippets

Open-source Python framework for building and orchestrating multi-agent AI systems

Open-source terminal agent that runs on your machine with any model

MCP platform with SDKs, desktop IDE and managed hosting for MCP servers
Offline review that flags agent changes which weaken tests, assertions or CI
Runs locallyConnect ChatGPT or Claude to store, CRM and shipping APIs without sharing keys
Not checked yetMessaging and advisory locks so several Claude Code sessions can share one repository
Runs locallyRead-only audit of agent skills in one workspace, plus a package manager for them
Runs locallyRun WCAG 2.2 accessibility audits and vision simulations on any URL from an agent
Runs locallyStops AI coding agents stuck in error loops and tracks token spend across tools
Shared, audited git, test and workflow tools for MCP coding apps that never push
Runs locallyDeterministic long-term memory and code search for coding agents, with no LLM calls
Searches your own code, PDFs and Office files and returns exact source citations
Runs locally