Awesome Agent Harness

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

🙌 OpenHands: AI-Driven Development

Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code

AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,600+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

Build, run, and manage agent platforms.

the runtime your coding agents live on

Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, and Google Antigravity

A reliable coding agent for complex software engineering tasks.

An open-source AI coding agent that lives in your terminal.

The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Orchestrate multiple coding agents from desktop and mobile

Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)

Devon: An open-source pair programmer

Laminar - open-source observability platform purpose-built for AI agents. YC S24.

A model-driven harness for AI coding agents: semantic modeling, app generation, progressive API Assist and evidence-based verification.

Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development, TDD, persistent memory, quality gates, code intelligence, human oversight, and end-to-end verification.

Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and parity enforcement. For Claude Code, Cursor, Gemini CLI, Codex and more.

The multi-agent harness that checks the work: verifies agent runs by artifacts (stop-hook gates, independent judges, append-only event logs) across Claude Code, Codex, Cursor, and 10+ runtimes.

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

Remote approvals, policy checks, and execution evidence for unattended AI agents.