This is an early release preview. You may encounter bugs.

Code with an agent

Agents and libraries that read, write and review code in your repo.

65 tools · showing 1–24

Coding +1

Goose

Rust-built local agent with desktop, CLI, and API surfaces, 15+ model providers, and 70+ MCP extensions

A+
Coding

Maka

Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and terminatio

A+
Coding +2

mcpContextForge

Registry and proxy that federates MCP, A2A, and REST/gRPC APIs behind one endpoint with governance, discovery, and observability

A+
Coding +1

OpenHands

Self-hosted control center running OpenHands, Claude Code, Codex, or any ACP agent across local, Docker, VM, and cloud backends

A+
Coding +2

OpenAI Agents SDK

Python framework for multi-agent workflows with handoffs, guardrails, sessions, sandbox and voice agents, and built-in tracing

A+
Coding +1

Omnigent

Open-source meta-harness that orchestrates Claude Code, Codex, Cursor, and custom agents behind one interface with policies and sandboxing

A+
Coding

Gh Aw

GitHub Agentic Workflows

A
Coding +1

OpenDesign

The open-source Claude Design alternative

A
Coding

Code Interpreter

Run AI-generated code in secure isolated cloud sandboxes via a JavaScript or Python SDK

A
Coding

DeepSeek-Reasonix

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

A
Coding +1

E2B

Runs AI-generated code in isolated cloud sandboxes controlled from JavaScript or Python SDKs

A
Monitoring +1

Omnara

Open-source platform for running managed agents with crash-safe state, launched from a console, Slack, a CLI, or an API

A
Deployment +2

ToolJet

ToolJet is the open-source foundation of ToolJet AI - the enterprise app generation platform for building internal tools, dashboard, business applications, workflows and AI agents

A
Coding

BentoML

Python framework for turning AI models into inference APIs and multi-model serving systems

A
Deployment +1

Dagger

Programmable container engine with SDKs and an MCP interface, used to run agent workflows and CI pipelines in reproducible containers.

A
Deployment +1

HarnessRouter

HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, H

A
Deployment +1

LMCache

A KV Cache Management Layer for Scalable LLM Inference.

A
Coding +1

QuantDinger

Self-hosted AI trading platform for crypto, stocks and forex, from strategy generation through backtesting to paper and live execution

A
Coding +1

ZenML

Framework for ML and LLM pipelines that run across any infrastructure with tracking and containerization

A
Coding

CubeSandbox

Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

A
Coding +1

OpenClacky

The most Token-efficient open-source AI Agent

A
Coding +1

SmolVM

Open-source AI sandbox infrastructure with unified API for VMMs -- Firecracker, QEMU and libkrun.

A
Coding +2

AX

Sandboxes your task, wires up its workspace, fences its network, and helps you run billions of them per cluster. Either use a single task per agent, or compose as many as your agent needs.

A
Coding

AstronRPA

Agent-ready RPA suite with out-of-the-box automation tools. Built for individuals and enterprises.

A