AgentScout / By role / Open-source maintainers

AI agents for open-source maintainers (2026)

Review bots, docs servers, testing and security agents that help maintainers keep up with issues and pull requests. We picked the top tools for 5 jobs open-source maintainers do every day: 30 tools in all, 28 of them free or with a free tier.

Jump to: Review pull requests · Write and fix code · Keep docs current for agents · Test changes · Security testing

Free tools from AgentScout for open-source maintainers: Agent setup generator (AGENTS.md, CLAUDE.md) · llms.txt generator

How we picked: each section takes the tools matched to that task in our directory, putting tools whose category and stated use cases fit the task first, then ordering by tracked GitHub stars. No paid placements.

Review pull requests

Agents that read diffs, leave review comments and catch bugs before a pull request is merged. All 24 tools →

Open Code Review Open source
Alibaba's AI code review CLI that combines deterministic pipelines with an LLM agent to post line-level comments on Git diffs, using OpenAI or Anthropic models. · ★ 47,560
GitHub MCP Server Open source
GitHub's official MCP server for letting agents work with repositories, issues, pull requests and Actions. · ★ 33,663
Qodo Freemium
AI code review and testing agents that work in the IDE, the terminal and pull requests to catch issues before merge. · ★ 13,415
Open SWE Open source
LangChain's asynchronous coding agent that takes work from GitHub issues, Slack or Linear, implements it in an isolated sandbox and opens a pull request. · ★ 11,034
Emdash Open source
A free, open-source agentic development environment (YC W26) for running Claude Code, Codex and other coding agents in parallel, each in its own worktree, then reviewing diffs, PRs and CI in one place. · ★ 6,037
Shippie Open source
Extendable code review and QA agent that reads your diff, explores the codebase and posts focused review comments. · ★ 2,510

Write and fix code

Coding agents that write, edit and refactor code from plain-language requests, in your terminal, editor or browser. All 391 tools →

opencode Open source
Open-source terminal coding agent that works with many model providers. · ★ 213,329
Claude Code Paid
Anthropic's terminal coding agent that edits code, runs commands and handles git. · ★ 150,707
CC Switch Open source
Desktop manager for Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw and other coding agents that switches API providers in one click and manages MCP servers, skills and prompts. · ★ 145,685
OpenAI Codex CLI Open source
OpenAI's open-source coding agent for the terminal; also runs in the cloud. · ★ 129,112
Graphify Open source
Turns a codebase plus its docs, SQL schemas, configs and PDFs into a knowledge graph that coding agents can query. · ★ 127,237
Pi Open source
Minimal, extensible open-source terminal coding agent and agent toolkit from Earendil, with a multi-provider LLM API, TypeScript SDK, RPC mode and installable extensions, skills and themes. · ★ 116,073

Keep docs current for agents

MCP servers that give coding agents current, version-specific documentation, so they stop guessing at outdated APIs. All 8 tools →

Context7 Freemium
MCP server and platform that feeds coding agents up-to-date, version-specific library documentation. · ★ 63,157
GitMCP Open source
Free remote MCP server that gives agents up-to-date docs and code for any GitHub project. · ★ 8,465
Microsoft Learn MCP Source-available
Official Microsoft Learn MCP server giving agents up-to-date Microsoft documentation. · ★ 1,950
pg-aiguide Open source
Timescale's MCP server with PostgreSQL docs and best practices for agents. · ★ 1,870
Grounded Docs MCP Open source
Self-hosted MCP server that indexes up-to-date documentation from websites, GitHub, npm and PyPI so coding agents query the right version. · ★ 1,815
Ref Freemium
Token-efficient documentation search for coding agents. · ★ 1,183

Test changes

Agents that write and run tests, click through your app and report what breaks. All 25 tools →

Goose Open source
Extensible open-source AI agent that installs, runs, edits and tests code on your machine with any LLM and MCP extensions. · ★ 55,347
Midscene.js Open source
Vision-driven UI automation and E2E testing framework where a GUI agent carries out natural-language steps on web, mobile and desktop apps. · ★ 15,311
MCP Inspector Open source
Official developer tool for testing and debugging MCP servers through a web UI, CLI or terminal UI. · ★ 11,095
MobileBuildMCP Open source
Sentry's MCP server and CLI that gives coding agents build, test and run tools for iOS and macOS projects. · ★ 6,497
Unity MCP Open source
MCP tools and CLI that let AI agents develop and test inside the Unity engine. · ★ 4,482
NitroStack Open source + cloud
TypeScript framework with decorators and dependency injection for building, testing and deploying MCP servers and MCP apps, with a companion desktop studio. · ★ 2,524

Security testing

Agents that probe your app, code and smart contracts the way an attacker would: running penetration tests, red-teaming AI systems and flagging vulnerabilities with suggested fixes. All 16 tools →

Strix Open source + cloud
Open-source AI agents that run penetration tests on your app to find and help fix security vulnerabilities. · ★ 69,022
PentAGI Open source
Autonomous multi-agent system for running penetration testing tasks. · ★ 30,728
AI-Infra-Guard Open source
Tencent's AI red-teaming platform that scans agents, skills and MCP servers for risks. · ★ 6,887
Superagent Open source + cloud
SDK for AI agent safety that blocks prompt injections and unsafe tool calls, redacts PII and secrets, and runs red-team scenarios. · ★ 6,770
CyberStrike Open source
Terminal agent for authorized penetration testing that runs recon, vulnerability discovery and reporting with specialized security agents on your own LLM. · ★ 3,192
PentestAgent Open source
Agent framework for black-box security testing and bug bounty work. · ★ 3,188