Autonomous Coding Agents

Open-source coding agent with a Rust runtime, desktop and CLI interfaces, self-hosted remote access, and support for custom tools and skills.

Multi-provider proxy and launcher for Claude Code, Codex, and Pi with a local Admin UI to route coding agents to 31+ cloud and local LLM backends. MIT licensed.

Open-source background coding agent system inspired by Ramp's Inspect, supporting file and environment snapshots, cron-based automation, and multi-provider models. MIT licensed.

Full-featured open-source AI software engineer.

MCP-powered coding-focused cybersecurity agent framework for automated pentesting and bug-hunting workflows.

Open-source autonomous AI pentest platform and MCP host orchestrating 80+ offensive tools via per-tech offensive sub-agents, with Active Directory and Kubernetes support. GPL-3.0 licensed.

Autonomous penetration testing agent utilizing Model Context Protocol (MCP) toolchains, blackboard state space search, and structured reasoning.

Extensible on-machine AI agent for development tasks.

Safe and private runtime for autonomous AI agents with policy-driven execution boundaries and CLI integration.

Terminal-native autonomous coding agent.

Performance-oriented agent harness for coding agents with skills, memory, and security-aware orchestration across Claude Code, Codex, and more.

Terminal coding agent with hash-anchored edits, subagents, LSP, browser integrations, and terminal-native workflows.

Modular agent toolkit with terminal-first CLI, unified model/provider layer, and runtime integrations for coding workflows and TUI/web UIs.

Command-line pair-programming agent.

Terminal coding agent with hash-anchored edits, LSP integration, subagents, MCP support, and package ecosystem.

Minimal CLI coding agent by Mistral. Lightweight, fast, and designed for local development workflows.

Beautiful local-first coding agent running in your terminal. Built for privacy and control with support for multiple AI providers via OpenRouter.

Open-source AI agent that brings Gemini's power directly into your terminal. Supports code generation, shell execution, and file editing with full Apache 2.0 licensing.

Workflow engine for deterministic AI coding agents. Define development processes as YAML workflows (planning → implementation → validation → review → PR) with isolated Git worktrees for parallel execution. MIT licensed.

Lightweight coding agent for repository and issue-fixing workflows, designed for simple agentic software engineering experiments.

Open-source agentic coding assistant with IDE workflows, tool use, and support for local or OpenAI-compatible models.

Asynchronous coding agent from the LangChain ecosystem for background software engineering tasks.

Memory-first coding harness designed for long-lived agents that learn from experience. Persistent agents with portable memory across models (Claude, GPT, Gemini, GLM, Kimi). CLI and desktop app for macOS, Windows, and Linux. Apache 2.0 licensed.

Local-first AI coding workspace that orchestrates multi-model planning councils, git worktrees, and task loops. MIT licensed.