LiveKit Agents
Open-source framework for building realtime voice AI agents with Python, WebRTC, telephony, and MCP tools.
Open-source framework for building realtime voice AI agents with Python, WebRTC, telephony, and MCP tools.
Open-source coding agent orchestration that turns backlog issues into verified, review-ready pull requests.
Open-source agent skills and a Python service for removing AI provenance marks from owned text and files.
Connect ChatGPT planning and code review to Codex execution through a read-only workspace bridge.
Open-source terminal agent runtime for research, sandboxed file work, and parallel agent teams.
Open-source Kubernetes orchestration for stateful sandboxes, AI agent runtimes, and reinforcement learning workloads.
Open-source optimization of prompts, code, agent architectures, and configurations using LLM reflection.
Run Qwen Mixture-of-Experts models locally on Macs and iPhones by streaming expert weights from storage.
code-graph-rag indexes multi-language codebases for natural-language search, code editing and analysis.
Open-source AI agent workspace for coding, Mini Apps, and cross-device task control
Local AI IDE account management with account switching, quota monitoring and parallel application instances.
Local MCP gateway CLI for tool discovery, context compression and shared agent skills
Open-source long-term memory and cross-agent handoffs for AI coding CLIs.
Open-source AI red teaming with agent, skill, MCP, infrastructure and LLM security scanners.
Open-source agent orchestration for Claude Code, Codex and MCP clients, with swarms, memory and workflow controls.
Search and enrich people and companies through an MCP server with contact lookup and job-change scores.
Local-first session search, analytics, and token cost tracking for AI coding agents.
Local-first manga translation with OCR, inpainting, LLM translation, page editing, and layered PSD export.
An open-source CLI that lets AI agents control local and cloud iPhones and Android phones.
Desktop account management, API protocol conversion, and request routing for AI services.
Open-source CLI harnesses that let AI agents work with desktop software, developer tools, and services.
Open-source PyTorch distributed training and fine-tuning for language and vision-language models
Open-source AI gateway for enterprise model routing, access control, usage attribution, and cost governance.
Vision tools for text-only models in DeepSeek Harness, including image Q&A, screenshot OCR, and UI restoration.
Pack repositories into AI-friendly files with token counts, configurable exclusions, and optional code compression.
Open-source multi-agent deliberation for hard decisions across Claude Code, Codex, Gemini CLI, and OpenCode.
An agent skill that turns goals into prompts for builder-critic loops and blind quality comparisons.
Open-source AI agent for coding, research and parallel multi-model workflows from the command line.
Open-source AI agent orchestration with tasks, org charts, approvals, budgets, and shared skills.
Open-source context graphs, knowledge graphs, deterministic reasoning, and decision provenance for AI systems.
Open-source AI note-taking for Obsidian with linked Markdown notes, source citations and vault health checks.
Open-source orchestration for durable AI agents, stateful applications, and replayable workflows.
Open-source GitHub Action for Claude-powered security reviews of pull requests and code changes.
A Durable Object-backed virtual filesystem with pluggable shell, container and JavaScript execution.
Open-source coding and research agent with persistent Python sessions, subagents, and long-running autonomous workflows.
Local-first control plane for agent teams, with durable goals, decisions, ownership and evidence across sessions.