Open Source Agent Harnesses
Sort By:
Agent Harnesses
View 102 business solutionsBrowse free open source Agent Harnesses and projects below. Use the toggles on the left to filter open source Agent Harnesses by OS, license, language, programming language, and project status.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
1
DeepSeek Harness
DeepSeek Harness: Everything is a Plugin
DeepSeek Harness is an open-source agent harness built around the idea that every major capability should be replaceable as a plugin. It uses Cordis to compose model adapters, tools, session handling, agent loops, persistence, sandboxing, approvals, and interface layers into configurable profiles. Users can run a browser-based interface, select a workspace, configure DeepSeek or other compatible model endpoints, and launch agent sessions against local projects. Agents can read and edit files, execute commands, delegate work, and maintain plans. Durable session events make work replayable and support persistence, forking, and resuming. The project is currently a fast-moving developer preview, so compatibility-breaking changes are expected. -
2
ZCode
Z.ai's coding agent harness. Powerful, intelligent, extensible
ZCode is an open-source AI coding workspace that combines desktop, browser, and terminal interfaces around a shared agent runtime. The repository includes an Electron desktop app, web client, backend services, reusable UI packages, and the ZCode Agent CLI. Its terminal interface also serves as the agent runtime used by the other clients. Shared protocols, RPC components, provider integrations, persistence services, and client SDKs keep the different interfaces synchronized. Developers can run local desktop workspaces or prepare assets for remote workspace scenarios. The project uses a pnpm monorepo with React-based UI components and centralized build tooling. It is designed as a complete coding-agent environment rather than a standalone command-line assistant. -
3
OpenClaw
Your own personal AI assistant. Any OS. Any Platform.
OpenClaw (formerly Clawdbot/Moltbot) is an open-source, self-hosted autonomous AI assistant designed to run on user-controlled hardware and bridge conversational natural language with real-world task execution, effectively acting as a proactive digital assistant rather than a reactive chatbot. It lets you send instructions through familiar messaging platforms like WhatsApp, Telegram, Discord, Slack, Signal, iMessage, and more, and then interprets those instructions to carry out actions such as managing calendars, sending emails or messages, browsing the web, executing system commands, and coordinating workflows across services — all while maintaining long-term memory and context across sessions. Because it runs locally or on infrastructure you choose (like a personal computer, VPS, or Raspberry Pi), OpenClaw emphasizes data ownership, privacy, and full transparency into how your instructions are handled and what actions are taken, giving users autonomy over their AI workflows. -
4
Pi Agent
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI
Pi is an open-source AI agent toolkit and coding agent framework designed to help developers build, run, and extend intelligent AI-powered workflows. Developed by Earendil Works, the project includes a coding agent CLI, unified multi-provider LLM API, agent runtime, terminal UI library, and web UI components. Pi supports multiple AI providers such as OpenAI, Anthropic, and Google through a single consistent API layer, making it easier to integrate different models into applications and agents. The framework is built around extensibility, allowing developers to create custom tools, workflows, and autonomous coding experiences. Pi also encourages the sharing of real-world AI coding sessions to improve agent performance through practical usage data instead of synthetic benchmarks. With its modular architecture, active open-source community, and support for advanced agent capabilities, Pi provides a comprehensive foundation for building next-generation AI development tools and autonomous c -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
LobeHub
Workspace to find, build, and collaborate with AI agents
LobeHub is an all-in-one workspace designed to help humans and AI agents collaborate, grow, and evolve together. It treats AI agents as true teammates rather than one-off tools, enabling deeper context, continuity, and productivity. Users can build personalized agent teams that understand their workflows, preferences, and goals over time. LobeHub brings multiple models, tools, and modalities into a single unified environment under the user’s control. With built-in collaboration features, agents can work in parallel, share context, and support complex projects seamlessly. The platform is built around the idea of co-evolution, where both humans and agents continuously learn and improve together. -
6
Browser Harness
Self-healing browser harness that enables LLMs to complete any task
Browser Harness is a self-healing browser control system built to give language models direct and flexible access to a real Chrome browser through the Chrome DevTools Protocol. Its main philosophy is minimalism: instead of imposing a rigid framework, it exposes a very thin bridge so the agent can perform browser tasks with almost no abstraction in the way. A defining part of the project is that the agent can write or extend missing helper functions during a task, which is why the repository describes it as self-healing. The implementation is intentionally compact, with a small set of core files handling installation, day-to-day usage, helper methods, and the daemon layer that maintains the CDP websocket bridge. The repository also includes domain and interaction skills, suggesting that it is meant to be used as part of a broader agentic workflow rather than only as a low-level developer tool. -
7
Claw Code
AI agent harness for AI coding agents
Claw Code is an open-source AI agent harness project focused on building better tools for orchestrating and managing autonomous coding agents. It originated as a clean-room reimplementation inspired by the architecture of Claude Code, aiming to replicate core concepts without using proprietary code. The project provides a Python-based foundation for experimenting with agent workflows, tool integration, and task execution pipelines. It emphasizes harness engineering—how agents are structured, how they interact with tools, and how they maintain context during execution. The system is being actively expanded, with a Rust-based runtime in development to improve performance and memory safety. Overall, Claw Code serves as a research-driven platform for advancing agent-based software development systems. -
8
Raven
Self-evolving multi-agent ecosystem for all-domain collaboration
Raven is a pre-alpha multi-agent orchestration system that coordinates specialized agents through one persistent workspace. It ships with built-in agents for research, coding, visual design, and supervision of long-running jobs. Raven can also orchestrate third-party agents such as Claude Code, Codex, OpenCode, GitHub Copilot, Pi, and others. Its runtime is powered by EverOS, allowing user context, agent experience, and reusable knowledge to persist across sessions. The system can generate task graphs, delegate work, combine results, and evolve tools, skills, and workflows over time. Raven supports a terminal interface, web UI, plugins, provider routing, and self-hosted deployment. It is designed for complex, long-horizon work that benefits from collaboration among agents with different strengths. -
9
Desloppify
Agent harness to make your slop code well-engineered and beautiful
Desloppify is a utility-focused project aimed at improving the quality, structure, and clarity of generated or written text by removing redundancy, noise, and unnecessary verbosity. It is designed to “clean up” outputs, particularly those produced by AI systems, making them more concise, readable, and professional. The system likely applies heuristics or transformation rules to identify repetitive patterns, filler content, and stylistic inconsistencies. This makes it especially useful in workflows where AI-generated text needs to be refined before publication or use in production. It may also support integration into pipelines, allowing automatic post-processing of outputs. The project reflects a growing need to manage and optimize AI-generated content rather than simply produce it. Overall, desloppify acts as a refinement layer that enhances clarity and usability of textual outputs. -
One Monitoring Tool for IT, OT and Cloud | Free TrialModern infrastructure spans data centers, cloud platforms and factory floors, and every blind spot between them is a risk. PRTG supports SNMP, WMI, SSH and other standard protocols to monitor IT, OT and hybrid environments through one customizable dashboard. Build the views your team needs, from network health to application performance, without switching tools. Try PRTG free for 30 days now.
-
10
Griptape
Python framework for AI workflows and pipelines with chain of thought
The Griptape framework provides developers with the ability to create AI systems that operate across two dimensions: predictability and creativity. For predictability, Griptape enforces structures like sequential pipelines, DAG-based workflows, and long-term memory. To facilitate creativity, Griptape safely prompts LLMs with tools (keeping output data off prompt by using short-term memory), which connects them to external APIs and data stores. The framework allows developers to transition between those two dimensions effortlessly based on their use case. Griptape not only helps developers harness the potential of LLMs but also enforces trust boundaries, schema validation, and tool activity-level permissions. By doing so, Griptape maximizes LLMs’ reasoning while adhering to strict policies regarding their capabilities. -
11
KaibanJS
JS-native framework for building and managing multi-agent systems
JavaScript-native framework for building multi-agent AI systems. Multi-agent AI systems promise to revolutionize how we build interactive and intelligent applications. However, most AI frameworks cater to Python, leaving JavaScript developers at a disadvantage. KaibanJS fills this void by providing a first-of-its-kind, JavaScript-native framework designed specifically for building and integrating AI Agents. Harness the power of specialization by configuring AI agents to excel in distinct, critical functions within your projects. This approach enhances the effectiveness and efficiency of each task, moving beyond the limitations of generic AI. Just as professionals use specific tools to excel in their tasks, enable your AI agents to utilize tools like search engines, calculators, and more to perform specialized tasks with greater precision and efficiency. -
12
Deep Agents
The batteries-included agent harness
Deep Agents is an open-source, batteries-included agent harness designed for long-running, multi-step AI work. It provides an opinionated agent setup while allowing developers to override or replace individual pieces without forking the project. The framework is model-agnostic and works with tool-calling models from hosted providers, open-weight deployments, or local runtimes. Built on LangGraph, it includes persistence, checkpointing, streaming, and production-oriented orchestration. Agents can delegate to sub-agents, work with files, run shell commands, manage long contexts, and retain memory across sessions. It also supports human approval of tool calls, reusable skills, custom tools, and MCP servers. -
13
superplan-plugin
Superplan is a CLI-first execution system.
Superplan is an execution system for AI agents. It turns planning into actual execution inside your repository. Instead of vague plans, chat history, or TODO lists, Superplan forces work into clear, step-by-step tasks that agents can execute, track, and resume at any time. The CLI is designed for agents to follow, not for humans to run manually. You define the work; your agent executes it through Superplan's structured runtime. -
14
OpenAI Symphony
Symphony turns work into isolated, autonomous implementation runs
Symphony is an open-source framework designed to transform project tasks into autonomous implementation runs managed by AI coding agents. It allows teams to manage and prioritize work while the system automatically assigns coding agents to complete tasks. Instead of directly supervising AI agents, engineers can oversee higher-level workflows and project outcomes. Symphony integrates with project management tools to detect new tasks and initiate isolated environments where agents implement solutions. Each run generates proof of work such as CI results, pull requests, code reviews, and analysis to validate the completed task. By automating execution and verification, Symphony helps engineering teams scale development workflows with minimal manual oversight. -
15
Oh My OpenAgent
The best agent harness
Oh My OpenAgent is a large-scale, open-source agent orchestration framework that aims to provide a fully unified and extensible environment for AI-powered software development and automation. It builds on the idea that no single model is sufficient, instead enabling coordinated use of multiple models for reasoning, creativity, speed, and cost efficiency within a single workflow. The system is designed as a comprehensive agent harness where tasks are automatically decomposed, delegated, and executed across a network of specialized agents. It emphasizes openness and flexibility, allowing developers to integrate different providers and avoid dependency on any single ecosystem or vendor. The framework includes robust tooling for managing agent workflows, monitoring execution, and integrating external tools, making it suitable for complex, production-level use cases. It also fosters a strong community-driven development approach, with features evolving in real time. -
16
Excalibur
Excalibur is a highly opinionated agent harness
Excalibur is an experimental or utility-oriented project that appears to focus on enabling structured execution, control, or enhancement of workflows within AI or development environments. The system likely provides tools for managing tasks, orchestrating processes, or enhancing decision-making capabilities in automated systems. Its design suggests an emphasis on control and precision, allowing users to define how tasks are executed and monitored. It may include abstractions for handling inputs, outputs, and intermediate steps, enabling more predictable behavior in complex workflows. The architecture is likely modular, supporting customization and extension for different use cases. This makes it suitable for experimentation as well as integration into larger systems. Overall, excalibur represents a flexible tool for managing structured processes in AI-driven or automated environments. -
17
Langroid
Harness LLMs with Multi-Agent Programming
Given the remarkable abilities of recent Large Language Models (LLMs), there is an unprecedented opportunity to build intelligent applications powered by this transformative technology. The top question for any enterprise is: how best to harness the power of LLMs for complex applications? For technical and practical reasons, building LLM-powered applications is not as simple as throwing a task at an LLM system and expecting it to do it. Effectively leveraging LLMs at scale requires a principled programming framework. In particular, there is often a need to maintain multiple LLM conversations, each instructed in different ways, and "responsible" for different aspects of a task. -
18
oh-my-agent
Portable multi-agent harness for .agents-based skills, workflows
oh-my-agent is a flexible and extensible framework designed to simplify the creation, management, and orchestration of AI agents across various tasks and environments. It builds on the idea of modular agent systems, allowing developers to define specialized roles and capabilities that can be combined into larger workflows. The framework emphasizes usability, making it easier to configure agents, assign tasks, and manage interactions without requiring deep expertise in AI system design. It likely includes support for plugins or skills, enabling agents to extend their functionality through integrations with external tools. The system also focuses on coordination, allowing multiple agents to collaborate on complex tasks in a structured manner. Its architecture supports experimentation, making it suitable for both prototyping and iterative development. Overall, oh-my-agent provides a practical foundation for building and managing multi-agent systems. -
19
fibonacci-AI-coding-agent
Autonomous coding agent as an SDK, IDE extension, or CLI assistant.Ope
Fibonacci is a native Iranian artificial intelligence tool, a comprehensive platform for the production of text, image content and intelligent programming assistant, API service and automatic content generation for articles, blogs, advertisements, media, etc. in 37 languages. -
20
Null-CLi
Secure The Unknown
NullSquare is an AI-powered security platform that can do both penetration testing and compliance auditing. -
21
Caprock
Free desktop app for Claude Code, Codex and OpenCode
Caprock is a free, open-source desktop app for AI coding agents, for macOS, Windows and Linux. It puts Claude Code, Codex and OpenCode sessions — including the ones you start in your own terminal — and the Gemini CLI sessions it starts into one window: terminals and projects in tabs and split panes, with activity, cost, plan limits and loop alerts for every session. Cost is per repository and per model, priced at API list prices from the tokens the agents already record, next to the 5-hour and weekly plan-limit windows. Everything the agent wrote is searchable across sessions and kept after Claude Code's 30-day transcript cleanup. A phone can carry on the work. It works with the subscription you already have. A daemon on loopback records sessions into a local SQLite database: no account, no hosted service, no telemetry. Free under Apache-2.0; an optional Premium licence adds paid features on top. -
22
AlphaClaw
OpenClaw harness and fleet manager.
AlphaClaw is an open-source management layer and deployment harness built on top of OpenClaw to simplify running and maintaining AI agents. It provides a browser-based interface that replaces manual CLI workflows with an intuitive setup and management experience. Designed for reliability, AlphaClaw includes a self-healing watchdog system that detects crashes, performs repairs, and automatically restarts the agent environment. It integrates with multiple platforms such as Slack, Discord, Telegram, and Google Workspace, enabling seamless multi-agent orchestration. The system also includes Git-backed version control and prompt hardening to ensure agents remain consistent, auditable, and well-behaved over time. AlphaClaw is ideal for developers and teams who want production-ready AI agents without the complexity of manual infrastructure management. -
23
Apodex FrontierAgent
FrontierAgent, our agent framework, open-sourced alongside it
FrontierAgent is an open-source agent runtime, terminal application, and evaluation suite for long-horizon research and file-based work. Its ReAct workflow provides a stateful agent that can research, read files, execute commands, and create deliverables inside a task-scoped sandbox. Agent Team mode adds a coordinator that divides work among parallel sub-agents and synthesizes their results. A live task board tracks pending, active, completed, blocked, and canceled work. Users can provide new instructions while an agent is running without discarding the active session. The same modular workflow engine also powers benchmark evaluations and can connect to OpenAI-compatible model endpoints. -
24
Egregor
Egregor — Local-first desktop Multi-AI Consilium
Egregor — это локальное десктопное приложение, которое объединяет несколько моделей ИИ (Claude, GPT, Gemini, DeepSeek и 300+ через OpenRouter) в структурированный «консилиум», где они обсуждают и сверяют ответы друг друга. Включает защиту от группового мышления, карту доверия и конвейер аудита смарт-контрактов. Все данные проекта остаются на собственном компьютере пользователя