Open Source AI Agents Apps

An open-source runtime control plane for AI agents — define safety guardrails once, apply them across agents built on LangChain, CrewAI, Google ADK, or AWS Strands, and update controls without redeploying code.

A self-hosted email client with an AI agent that reads your inbox, drafts replies automatically, and exposes full email operations over MCP — running entirely on Cloudflare Workers.

Persistent memory for AI coding agents — built on the iii engine, it works across Claude Code, GitHub Copilot CLI, Cursor, Gemini CLI, Codex CLI, and any MCP client, so agents stop needing everything re-explained every session.

Free, open-source Cowork desktop app that unifies Claude Code, Codex, Gemini CLI, and 20+ AI agents into a single platform with multi-agent teams, 24/7 cron automation, and zero-config built-in agent.

Give an AI agent a real LLM training setup and let it experiment autonomously overnight — you wake up to a log of experiments and (hopefully) a better model.

Unified open-source platform for AI agent orchestration and workflow automation with 180+ connectors, MCP support, and durable execution.

A portable memory layer for AI coding agents — curate structured project knowledge into a version-controlled context tree that syncs across tools, machines, and teammates.

A local-first desktop workspace for managing AI agents in an enterprise-style workflow — agent directory, Kanban task tracking, workspace chat, and a full runtime/audit log of agent actions and tool approvals.

Give your AI coding agents persistent memory — claude-mem captures everything that happens during sessions, compresses it with AI, and surfaces the right context in every future session automatically.

A Rust-built CLI agent harness for Claude AI with persistent sessions, MCP tool integration, plugin hooks, and multi-provider support — designed to run autonomous coding workflows without human babysitting.

Run Claw AI agents entirely in the browser — no server required — with WebContainers WASM sandboxing, policy enforcement, and complete audit logging.

The batteries-included Python agent harness — planning, sub-agents, filesystem, shell, memory, and skills bundled in, built on LangGraph.

An AI-native CRM you self-host on your own machine, built on the OpenClaw agent framework, with a DuckDB backend and pre-built agent skills for managing contacts, deals, reports, and 500+ outreach integrations from natural-language chat.

Give your AI agents a real, authenticated email address — with SPF/DKIM-verified inbound, HMAC-signed delivery, WebSocket fan-out, and human-in-the-loop approval built in.

Build, debug, and deploy knowledge-based AI agents with a visual workflow editor, RAG retrieval, and support for any OpenAI-compatible LLM.

Build autonomous AI agents and powerful workflows with a programmable TypeScript harness that gives any model sessions, tools, sandboxes, and durable execution.

A YC-backed, open-source knowledge graph skill for AI coding assistants — type /graphify and it maps your entire project (code, docs, PDFs, images, videos) into a queryable graph instead of grepping through files.

A biologically-inspired memory layer for AI coding agents — memories decay by default and strengthen through use, modeled on the hippocampus, with zero runtime dependencies and a SQLite backbone.

Open-source AI creative agent that turns visual sketches and canvas gestures into images and videos — no text prompts required.

kubectl for AI Agents — manage, schedule, and scale your AI workforce with a single binary that deploys in seconds.

Build, test, and deploy AI agents and RAG workflows visually with native API and MCP server export.

Open-source AI agent monitoring that catches what will break next before your users do.

Local-first AI memory with verbatim storage, pluggable backends, and 96.6% retrieval recall on LongMemEval — no API key required.

The open-source, self-hostable workspace that delegates entire tasks to swappable AI agents and hands back finished, shareable artifacts instead of another chat reply.

A universal swarm intelligence engine that spawns thousands of autonomous AI agents to simulate and predict how real-world events unfold across social, financial, and political domains.

Self-hostable platform for running autonomous coding agents in isolated, credentialless sandboxes with brokered credentials, reusable snapshots, and event-driven triggers.

A local-first AI memory sidecar that extracts entities, builds a persistent knowledge graph, and injects ranked context into any LLM pipeline — no cloud required.

A privacy-first personal API gateway for AI agents — connect your services once, issue scoped tokens to agents like OpenClaw, Hermes, or Claude Code, and keep a full audit trail instead of scattering raw credentials across .env files.

Run AI coding agents like OpenClaw and Hermes securely inside NVIDIA OpenShell sandboxes with a hardened blueprint, routed inference, and lifecycle management through a single CLI.

An open-source MCP platform for organizations — host MCP servers, run MCP registries, monitor usage, and build agents and chatbots on top of the Model Context Protocol from one self-hosted deployment.

A lightweight, stealthy headless browser written in Rust — drop-in compatible with Puppeteer and Playwright, built for AI agents and web scraping at scale.

Multi-agent orchestration for Claude Code with zero learning curve — install as a plugin or npm CLI and coordinate parallel Claude Code agents through pre-built workflows instead of managing them by hand.

A free, open-source AI gateway connecting Claude Code, Codex, Cursor, Cline, and Copilot to 237 AI providers (90+ free) through one endpoint, with automatic fallback and token-compression to stretch free-tier limits further.

Self-hostable AI platform with agentic RAG, 50+ connectors, deep research, code execution, and support for every major LLM provider.

Open-source reference app for building and running background AI coding agents on Vercel — from chat prompt to committed code changes without keeping your laptop involved.

Create automated AI scouts that continuously search the web and send email alerts when they find what you're looking for.

The extensible, privacy-first AI platform that runs Ollama, OpenAI, and any LLM backend behind a polished, feature-packed web interface.

Run Claude Code workflows against any LLM — OpenAI, Gemini, Ollama, and 200+ backends — from a single terminal-first CLI.

An open-source "Agent Operating System" built in Rust — a single binary providing a kernel, memory, skills, extensions, and multi-channel runtime for running AI agents, with 1,700+ tests and zero clippy warnings.

The safe, private runtime that lets autonomous AI agents operate in sandboxed environments governed by declarative YAML policies — blocking data exfiltration, credential leaks, and unauthorized network activity before they happen.

Opslane's /verify plugin turns a pasted PM ticket into a browser-driven acceptance-criteria check inside Claude Code, screenshotting and video-recording every pass or fail before you push.

Self-hosted AI agent workflow orchestration that runs on your Kubernetes cluster — from ticket intake to squash-merged PR, entirely within your infrastructure.

An open-source Agent Development Environment that orchestrates fleets of parallel AI coding agents — Claude Code, Codex, Gemini and more — each running in its own isolated git worktree.

The native macOS AI harness that keeps your agents, memory, tools, and cryptographic identity on your machine — not a company's servers.

Control any web interface with natural language — no browser extension, no headless browser, just a JavaScript script tag.

The open-source control plane that turns a pile of AI agents into an actual company — with org charts, budgets, heartbeats, and governance.

One unified interface to orchestrate Claude Code, Codex, Copilot, OpenCode, and Pi agents in parallel from desktop, mobile, or the terminal.

The first AI agent harness native to the browser — a Chrome/Firefox extension that drives your tabs, spins up sandboxed compute (JS notebooks, WASM Linux VMs), and shares what it builds peer-to-peer, with no backend, no telemetry, and BYOK.

An open-source, self-extensible agent harness and coding agent CLI — a modular runtime (agent core, unified multi-provider LLM API, TUI) with no built-in permission system by default, documented containerization patterns for sandboxing instead.

Open source AI-first sales platform that replaces Salesforce with autonomous agents handling prospecting, outreach, and lead management at scale.

An npm-native, drop-in LLM proxy for Node.js — swap in as your OpenAI/Anthropic base URL to get per-request cost tracking, task-aware routing, budget enforcement, and anomaly detection running locally, for free.

Stateful actors as a primitive for AI agents, real-time collaboration, and durable execution — with in-memory state, WebSockets, queues, and scheduling built in.

An open, self-hostable, multi-model agent runtime that deploys any agent skill as an API via POST /run — an open-source alternative to Claude Managed Agents and Google's Gemini Enterprise Agent Platform.

Skyvern (YC S2023) automates browser-based workflows by pairing LLMs with computer vision, letting agents click, fill, and extract data on sites they've never seen, without brittle XPath selectors that break on every layout change.

Turn your company into a git repo — one config, one command center, a workforce of AI agents that runs the real work around the clock.

An open-source SDK that blocks prompt injections, redacts PII and secrets, scans repositories for AI-targeted attacks, and red-teams production agents.

superglue is an AI-agent-driven integration engine that turns plain-English descriptions of enterprise systems into production-grade API tools, ERP/CRM connectors, and data pipelines — self-hosted or cloud, Y Combinator-backed (W25).

Open-source agentic observability that ingests OpenTelemetry signals, groups them into incidents, and deploys AI agents to investigate and fix your production bugs automatically.

Symphony turns your issue tracker into an autonomous implementation engine—spawning isolated coding agents per ticket so your team manages work, not agents.

An open-source visual canvas for building AI workflows by connecting nodes across 35+ model providers with drag-and-drop simplicity.

Open-source AI-native platform to build and deploy internal tools, workflows, and AI agents with a visual drag-and-drop builder and 80+ data source integrations.

Open-source agentic security automation platform that runs AI agents and durable workflows at scale with sandboxed execution.

Open-source local AI agent that operates your entire computer — GUI, browser, shell, and messaging — from a single instruction, using your own models.

A security-focused, self-hostable AI agent platform for production work — agents run in isolated containers that access credentials only through a host-side proxy, so the AI itself never sees API keys or plaintext credentials.

A kanban board for planning work and dispatching Claude Code, Codex, Gemini CLI, and eight other coding agents into isolated git worktrees, then reviewing and merging their diffs from one UI.