Open Source AI Agents Apps
Discover open source AI agent frameworks, runtimes, and orchestration tools. Build autonomous agents that plan, use tools, and execute multi-step tasks.
Apps in AI Agents
Language
License
hyperresearch
AI Agents · Developer Tools · Knowledge Management
A tier-adaptive 16-step deep research pipeline for Claude Code that produces adversarially-audited reports with full source provenance, backed by a persistent, searchable vault.
OfficeCLI
AI Agents · Developer Tools · Productivity
A single-binary CLI that gives AI agents full read/write control over Word, Excel, and PowerPoint files — no Office installation, no dependencies, and a built-in HTML/PNG renderer that closes the render-look-fix loop.
qm
AI Agents · AI Assistants · Automation
An open-source, multiplayer agent harness that gives every employee and every room in a company its own scoped memory, sandbox, and AI agent — in Slack and on the web.
e2a
AI Agents · Automation
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.
NemoClaw
AI Agents · AI Development
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.
page-agent
AI Agents · Automation
Control any web interface with natural language — no browser extension, no headless browser, just a JavaScript script tag.
peerd
AI Agents
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.
Hippo
AI Agents · AI Memory
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.
OpenMontage
AI Agents · Video Editors
Open-source agentic video production system: your AI coding assistant researches, scripts, generates, edits and renders finished videos through approval-gated pipelines with budget controls.
RelayPlane
AI Agents
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.
Vibe Kanban
AI Agents · AI Code Assistants · Project Management
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.
Opslane
AI Agents · Developer Tools
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.
Magic
AI Agents · Automation · Low Code Platforms
Magic is an enterprise-grade open-source AI agent platform combining a generalist AI agent, workflow engine, IM, and collaborative office system for running an AI-powered digital workforce.
Superagent
AI Agents · Security
An open-source SDK that blocks prompt injections, redacts PII and secrets, scans repositories for AI-targeted attacks, and red-teams production agents.
superlog
AI Agents · Monitoring
Open-source agentic observability that ingests OpenTelemetry signals, groups them into incidents, and deploys AI agents to investigate and fix your production bugs automatically.
About AI Agents
AI Agents are autonomous software systems that go beyond chatting — they perceive context, plan multi-step workflows, call external tools, write and execute code, and loop until a goal is achieved. Unlike traditional AI assistants that respond to single prompts, agents operate over extended horizons, recovering from failures and adapting to new information.
The open-source ecosystem has exploded with agent frameworks, runtimes, memory systems, and orchestration layers — giving developers full control over how agents reason, what tools they access, and how they handle long-running tasks without being locked into a proprietary platform.