Open Source AI Agents
Discover 404 open source AI Agents repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. AI Agents projects here are most often combined with Python, Developer Tools and MCP. Last updated October 4, 2026.
404 repositories · updated October 4, 2026
maka: Run and Inspect AI Agent Workflows
Apache Maka is an agent workspace that records model messages, tool calls, and permission decisions as an append-only event log. It is aimed at people building or evaluating agents who want local session data and a recoverable execution history.
OpenMausBot: Coordinate AI Agents in a Desktop Chat App
OpenMausBot is a local-first desktop app for managing AI agents as a team of chat contacts. It runs supported agent CLIs on your computer and can connect agents to computers and third-party apps, with approval prompts for risky actions.
agentic-engineering: Give Coding Agents a Persistent Project Workflow
A documentation-first skill suite for coding agents, covering project specs, decisions, session memory, verification, and Git workflow. It suits teams running multi-session development who want agents to follow explicit contracts and leave merges to humans.
gitnexus: Map Codebases for AI-Assisted Exploration
GitNexus indexes a repository into a code knowledge graph so developers and AI coding agents can trace dependencies, call chains, and execution flows. Use its local CLI and MCP integration for ongoing work, or the browser UI for quick exploration.
agentskit: Build AI Agents in JavaScript
AgentsKit is a TypeScript toolkit for building JavaScript AI agents from composable packages for model adapters, runtime, tools, memory, retrieval, and user interfaces. It suits developers who need more than a chat SDK and want to keep provider and component choices flexible.
aport-agent-guardrails: Authorize AI Agent Actions Before Execution
APort adds policy checks before supported AI agent tools run, helping teams limit prompt-injection risks and unauthorized actions. It provides runtime integrations and GitHub repository checks, with local or hosted verification options.
aiwg: Reuse AI Workflows Across Coding Tools
AIWG deploys reusable project context, specialist agents, and structured workflows to multiple AI coding tools. It helps individuals and teams carry decisions, reviews, and procedures across tasks and sessions.
awesome-ai-coding-sandboxes: Compare Agent Code Sandboxes
A curated, security-focused directory of sandboxes for running AI coding agents' code. Compare isolation boundaries, network egress controls, secrets handling, hosting options, and workspace state to shortlist tools for further evaluation.
uta: Coordinate Coding Agents Across CLI Providers
uta is a Go CLI that breaks goals into parallel tasks, routes them to installed coding-agent CLIs, and records each run for review or continuation. It suits developers who need cross-provider orchestration and traceable agent workflows.
aport-spec: Define Pre-Action Authorization for AI Agents
aport-spec defines the Open Agent Passport (OAP), a draft specification for verifying and authorizing AI agent actions before they occur. It is aimed at platform builders and developers implementing runtime policies, signed decisions, and interoperable agent credentials.
open-code-review: Review Code with an AI-Powered CLI
Open Code Review combines deterministic review steps with an LLM agent to inspect code changes and produce line-level comments. It suits teams that want configurable AI reviews in local workflows or CI, with Git 2.41 or newer and an LLM endpoint for managed reviews.
CyberVerse: Build Self-Hosted Voice-First AI Agents
CyberVerse is a self-hosted framework for real-time voice agents with persistent character memory, tools, and retrieval-augmented generation. It can also stream digital-human video, for teams building interactive assistants with configurable model providers.