Tools tagged with "Agent Harness"

OpenClaw is an open-source AI assistant that runs on your machine and works from WhatsApp, Telegram, or any chat app, handling tasks like inbox, email, calendar, and flights. No subscription, no hosted tier, and no token required.

DeepSeek Harness (dsh) is an open-source agent harness in developer preview. Every agent capability is implemented as a composable Cordis plugin for models, tools, skills, sessions, sandboxes, storage, loops, scheduling, and the UI.

OpenCode is an open-source AI coding agent that runs in your terminal, featuring built-in agents for development and planning, and a desktop app in beta.

LangChain is the agent engineering platform and provides create_agent, a minimal, highly configurable agent harness for composing an agent from model, tools, prompt, and middleware.

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Open-source AI coding agent that runs in your IDE, terminal, and desktop. Supports Plan/Act modes, MCP integration, and works with every major model provider. Trusted by 11M+ developers.

OpenHuman is a free, open-source personal AI for Mac, Windows and Linux that keeps data local and orchestrates fleets of agents. Built in Rust, it is positioned as a fast, efficient open-source agent harness.

omp is a coding agent for the terminal with subagents, plan mode, LSP, DAP, memory, hashline edits, and time-traveling rules, powered by a native Rust core. Built by Stencil Labs.

SpaceXAI's terminal-based AI coding agent with a full-screen TUI. It understands your codebase, edits files, executes shell commands, searches the web, and manages long-running tasks. Works interactively, headlessly for scripting/CI, or

T3 Code is the open-source control plane for coding agents, orchestrating Claude Code, Codex, Antigravity, OpenCode, Cursor, and Grok from one surface.

SWE-agent lets your language model autonomously use tools to fix GitHub issues, find cybersecurity vulnerabilities, or perform custom coding tasks. Built by Princeton and Stanford researchers, it achieves state-of-the-art results on

Browser Harness is a thin, self-healing harness for browser agents built directly on CDP. Agents can edit their own helpers mid-task, so the harness improves with every task and enables LLMs to complete browser tasks.

Harbor is a framework from the creators of Terminal-Bench for evaluating and optimizing agents and language models in container environments. It supports arbitrary agents, custom benchmarks, parallel cloud experiments, and rollouts for RL

magpie is a menu bar app that lets you pick the model each AI coding agent uses, routing Codex, Claude Code, Gemini CLI and others through one local gateway to providers such as DeepSeek, Kimi and GLM.

Open-source infrastructure that runs harnesses like Codex, Claude Code, and Hermes as pluggable agent backends, letting products run tasks, retrieve results, and switch harnesses through one API.

cf is the agentic CLI for the entire Cloudflare API. It offers agent-friendly command search and steering, JSON output by default, cloudflare.config.ts configuration for Workers, and Vite as the default dev server.