agent-harness
a continuous-improvement harness for long-running agent tasks. Turns Claude Code, Codex, or Hermes into a multi-agent mission orchestrator via MCP/ACP.
Zenith is an agent harness for work that may run for days or weeks, where the dominant failure mode is premature completion rather than inability to make progress. It runs a coding agent (Claude Code, Codex, or Hermes) as a multi-agent orchestrator over MCP/ACP: one orchestrator session reads task state each turn and decides whether to spawn workers and testers, register reusable skills, replan, or stop.
An IDE designed for agentic AI research. AgentsDock currently supports Claude Code, Codex, and Cursor in one desktop and mobile workspace.
Your team’s control room for coding agents.
Self-hosted agent-infrastructure server: a web UI plus Slack, Linear, Plain, and GitHub agents, driving coding sessions through the Pi engine in git worktrees on your own box, or in isolated sandboxes. Supports multiple Codex and Claude subscriptions and model APIs.
Your repo gets better while you sleep. Nightly agent jobs and PR review for any repo.
Nightshift is a helper that works at night.
It wakes up your coding agent. It gives the agent one small job. The agent looks at your code and does the job. If it finds something worth fixing, it opens a pull request for you to look at. Then it moves to the next job.
Local-first AI coding agent desktop: Electron + Rust host core + pi Agent Harness + user-installable plugins
A hive mind communication platform.
A workspace where humans and agents build together, on a relay you own.
Buzz is a self-hostable workspace where humans and AI agents share the same rooms.
A Buzz community is the workspace a user reaches by URL. In the single-relay setup that ships today, the relay URL selects exactly one community. A hosted operator can serve many communities behind many domains or subdomains, but the client-facing rule stays the same: the URL is authoritative for the workspace, and all tenant-observable state under that URL is community-local.
An open source terminal coding agent, written in Rust.
The most RAM efficient harness. The most intelligent harness. jcode is built to be as performant and resource efficient as possible. Every metric is optimized to the bone, which is important for scaling multi-session workflows. Here we sample a few metrics to show the difference: RAM usage and boot up.
runs anywhere. uses anything. open-source coding agent CLI for any model
not a chatbot wrapper or another ide plugin. an open coding agent that runs in your terminal, talks to any model, and keeps every change reviewable.
Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.
exoharness is a minimal architecture for building agents. It separates trusted infrastructure for state, resources, and security from agent-specific logic that can evolve, stop, resume, and rewind across runs.
Exo is a systems approach to recursive self improvement. In short, it's a complete AI agent harness (supporting tools, tasks, integrations, etc. similar to OpenClaw, Pi or Hermes), with the crucial difference that it has full visibility into both its code and runtime logs. This allows Exo to incrementally improve every aspect of itself, clone itself, and even manage a lineage of clones.
Pentest Harness — Heaven for Hackers. A self-hosted AI agent harness for authorized pentests, bug bounty, security labs, and CTFs. Bring your own AI model API; sessions stay local.
An open-source, dark-first AI agent harness for authorized penetration tests, bug bounty research, security labs, and CTF engagements. Built on a plugin architecture where every layer — model adapters, tools, sessions, settings, and credentials — is replaceable from configuration.
Works with any AI model API. Bring your own key from OpenAI, Anthropic, DeepSeek, Google, Mistral, Groq, OpenRouter, Azure OpenAI, or any OpenAI-compatible gateway — one click auto-discovers your models and you're running.
An LLM tool-use loop (bash / read / write / edit / subagent), an interactive bubbletea session, and provider-routable models. One binary, no runtime, config you can read.
A fast coding-agent harness in Go. Tool-use loop, bubbletea TUI, provider-routable models with live catalog discovery, MCP support, background subagents. One binary, no runtime, built for open-source models.
Local-First AI Agent Workspace.
A local-first Agent workspace built for real work. Maka inspects projects, runs tools under a sandbox boundary, and records model messages and tool calls as recoverable execution facts — on your machine, through one Runtime Host.
Run a team of coding agents.
The open-source AI IDE for Claude Code, Codex, OpenCode, and more. Run agents in parallel, locally or in the cloud, and build reusable workflows.
Control your coding agents (Claude Code, Codex, Cursor, Grok, Hermes, Pi) locally by default, with optional multi-device sync.
Every device runs a small engine that stores sessions on that device. A new installation starts in local-only mode without an account or a network connection.
A multi-model AI agent desktop client — connect any AI provider, extend with MCP & skills, control from your phone. Built with Electron + Next.js.
One window — every project, every agent.
Silo — for developers juggling coding agents across many projects. Every workspace alive at once, switch instantly. 100% open source, free forever.
Learn to build AI agents locally without frameworks
Understand what happens under the hood before using production frameworks. Build real understanding of function calling, memory, and ReAct patterns.
a coding agent you can leave running.
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
One local engine, four ways in — terminal, desktop app, browser, or your editor over ACP. Plan mode, permissions, a workspace sandbox and per-turn checkpoints keep a long autonomous run something you can still read and undo.
Agent harness to run an office of your clones. local multi-agent harness.
Free, open source and performant — a multi-agent harness that works with the subscriptions you already pay for, on their hourly limits. It turns the terminal coding CLI you already run into a clone of you, one that keeps working while you're away and coordinates a whole office of agents on your own machine.
Wraps Claude Code, Antigravity (Gemini), OpenAI Codex, xAI Grok, Kimi Code, Qwen, OpenCode, Crush, pi.dev, and GitHub Copilot CLI — with bring-your-own keys and local LLMs. Agents that message, route, and remember, coordinated by your clone (Michael) and visualized as avatars at work on a shared office floor.
Tiny, open, native coding agent.
fx is a coding agent harness and CLI written in Zig, optimized for research and embeddability as part of larger systems.
Open-source Grok Bot alternative. Choose your own model and sandbox.
Web, desktop, and mobile. Bring your own AI and sandbox. The product is still early (beta).
Each bot has one thread, one computer, memory, routines, and history. A bot can also spawn more bots — each a regular peer with its own thread and computer — or run short-lived subagents inside the current turn. This repository is the complete core product — it runs without a Rakazo-operated control plane.
The app people use to manage AI agents for work.
Open-source orchestration for teams of AI agents.
If OpenClaw is an employee, Paperclip is the company.
Paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. Bring your own agents, assign goals, and track work and costs from one dashboard.
Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude Code or Codex, with none of their dependencies or model constraints.
Ante is designed for cellular-native agents: like cells in an organism, tiny, expendable, massively replicated.
the IDE for loop-driven development.
bb is an agentic IDE that can control itself. You can seamlessly orchestrate all of your favorite coding agents together and have them programmatically use bb too.
Related contents:
Agent-driven research knowledge base. Agents collect, search, and synthesize web research into a persistent, searchable wiki.
Hyperresearch turns Claude Code into a deep research agent: one that currently leads the DeepResearch-Bench RACE leaderboard (benchmarked internally). A tier-adaptive 16-step pipeline takes one prompt and produces an adversarially-audited report with full source provenance. Every source it reads lands in a persistent, searchable vault, so each session starts smarter than the last.
Agentic SAST Pipeline.
VVAH is Visa's open-source harness for autonomous vulnerability discovery, remediation, and validation using frontier AI models, built on learnings from Project Glasswing (Anthropic's initiative for AI-assisted vulnerability research).
Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one setup script.
Simple, Fast, Vibe‑Ready ! Official Harness for GLM-5.2.
ZCode combines the best AI agents with your existing tools so you can plan, code, review, and deploy without friction.
Godcoder doesn't just use a harness. It writes one, improves it, and optimizes it — autonomously, in real time.
A local-first, open-source coding agent for your desktop. Bring your own LLM key; your code stays on your machine and only ever leaves to the model provider. The AI Agent builds its own Harness.
peerd is an extension that turns your existing browser into an agent workstation.
The first AI agent harness native to the browser. A Chrome/Firefox extension that runs the agent loop in your browser — drives your tabs, spins up sandboxed compute (JS notebooks, WASM Linux VMs, client-side apps), and shares what it builds peer-to-peer. BYOK · no backend · no telemetry.
Three primitives. Zero integration cost.
Effortlessly compose, extend, and observe every service in real-time for the first time ever. iii is the easiest way to compose, extend, and observe every service in your stack in real time.
Every backend starts as a project before the first line of business logic. Queues, cron, HTTP, state, observability, agents, and sandboxes each usually bring their own integration story. iii collapses that into one live system surface.
A reference implementation for autonomous vulnerability discovery and remediation with Claude.
Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize.
Own your AI.
The native macOS harness for AI agents that run on your machine. Any model. Your files. Your memory. Free and open source.
Related contents:
Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents.
deepsec an agent-powered vulnerability scanner that you can run in your own infrastructure, optimized to perform on-demand review of all code in existing large-scale repos.
Related contents:
Bring any AI model into your terminal.
A fully decentralized fork of Warp. Six native AI protocols, third-party CLI agents as first-class Blocks, a built-in SSH + tmux host manager. Every credential, conversation and key stays on your machine.
Build a workspace for work that unfolds over time. The Computer for You and Your Agent.
Describe one long-running job. Download holaOS, kick it off in seconds, and a workspace builds itself — with goals, context, rules, and a next run.
The Agent Harness Framework. The sandbox agent framework.
Not another SDK. Build powerful, autonomous agents with Flue's programmable TypeScript harness. Write once, deploy anywhere.
Flue is a TypeScript framework for building the next generation of agents, designed around a built-in agent harness. It's like Claude Code, but 100% headless and programmable. There's no baked-in assumption like requiring a human operator to function. No TUI. No GUI. Just TypeScript.
Related contents:
Coding Agent Harness.
The next generation coding agent harness to raise the skill ceiling. Built for multi-session workflows, infinite customizability, and performance.
zero package dependencies, under 50KB. a slop cannon small enough to fit your pocket.
A zero-package-dependency coding agent under 50KB. Pronounced exactly how you think.
AI Framework & Toolkit for Claude Code & Cursor.
AI’s capabilities grow like vines: full of vitality but spreading everywhere. Trellis is scaffolding for AI, guiding it along the path of your conventions.
Package your AI coding workflows as YAML. Run them anywhere — CLI, Web, Slack, Telegram, GitHub, Discord.
The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.
Open Agent Harness.
OpenHarness delivers core lightweight agent infrastructure: tool-use, skills, memory, and multi-agent coordination.
Related contents:
The Agent Operating System.
LibreFang is a production-grade runtime for autonomous AI agents. Single binary, 15 built-in capability units, 44 channel adapters. Built in Rust for the workloads that can't afford to go down. LibreFang is an Agent Operating System — a full platform for running autonomous AI agents, built from scratch in Rust. Not a chatbot framework, not a Python wrapper.
Traditional agent frameworks wait for you to type something. LibreFang runs agents that work for you — on schedules, 24/7, monitoring targets, generating leads, managing social media, and reporting to your dashboard.
Related contents:
Agent teammates that grow with you.
The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.
Related contents:
Skills, agents, and security for your coding agent. Open Agent Harness System for GitHub App Automation and Security.
Pick a profile. Install the skills and agents your team needs. AgentShield scans every session. The GitHub App turns repo history into reusable defaults. 140K+ stars on GitHub. Start free, scale to enterprise.
Architecture in. Software out. Spec-Driven Code Generation.
An open-source framework that turns architectural specs into working code. You write a specification, optionally lay out the architecture, and Ossature breaks it down into a build plan that gets executed step by step with an LLM doing the code generation under tight constraints. The specs are your source of truth, you review the plan before anything gets built, and when something breaks you fix that step and keep going instead of starting over.
Related contents:
An Open-Source Asynchronous Coding Agent. Open-source framework for building your org's internal coding agent.
Elite engineering orgs like Stripe, Ramp, and Coinbase are building their own internal coding agents — Slackbots, CLIs, and web apps that meet engineers where they already work. These agents are connected to internal systems with the right context, permissioning, and safety boundaries to operate with minimal human oversight.
Open SWE is the open-source version of this pattern. Built on LangGraph and Deep Agents, it gives you the same architecture those companies built internally: cloud sandboxes, Slack and Linear invocation, subagent orchestration, and automatic PR creation — ready to customize for your own codebase and workflows.
Related contents:
The batteries-included agent harness.
The easiest way to start building agents and applications powered by LLMs—with built-in capabilities for task planning, file systems for context management, subagent-spawning, and long-term memory. You can use deep agents for any task, including complex, multi-step tasks.
Agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic tasks.
Deep Agents is an agent harness. An opinionated, ready-to-run agent out of the box. Instead of wiring up prompts, tools, and context management yourself, you get a working agent immediately and customize what you need.
Related contents:
Give your agents access, not your secrets. The open-source secret vault for AI agents. Store once. Inject anywhere. Agents never see the keys.
Open-source credential vault. Your agents call services and never see a key.
OneCLI is an open-source gateway that sits between your AI agents and the services they call. Instead of baking API keys into every agent, you store credentials once in OneCLI and the gateway injects them transparently. Agents never see the secrets.