Awesome Agent Harness

Self-hosted TypeScript agent runtime with durable approvals and verifiable run records. Own it, approve it, audit it.

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

Agenta is a workspace where you and your team build agents and automations.

Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

Robust, fast, scalable, and sandboxed open-source online code execution system for humans and AI.

Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/

Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.

Evaluation and Tracking for LLM Experiments and AI Agents

Agent Orchestration Command Center

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

Sandbox any AI agent in seconds - zero setup, zero latency.

A HTTP credential proxy and vault for AI agents like Claude Code, OpenClaw, Hermes, custom agents + harnesses, and more.

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

Official Microsoft Learn MCP Server and CLI tool – powering LLMs and AI agents with real-time, trusted Microsoft docs & code samples.

A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.

Continual learning infra for self-improving agents

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.

The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)

Open-source benchmark for browser AI agents on daily tasks.

Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications

Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included

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

Deterministic safety solutions for probabilistic AI agents

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

Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.

Open Python agent harness for production AI apps: tools, MCP, memory, workspace, telemetry, subagents, background tasks, and OmniServe APIs.

Benchmark for comparing agent harnesses on everyday online tasks — fixes the base model, varies the harness. Sister project of ClawBench, same scoring pipeline.