cmux
Open-source macOS terminal with workspaces, split panes, browser automation, and notifications for AI coding agents.
Open-source macOS terminal with workspaces, split panes, browser automation, and notifications for AI coding agents.
Open-source reverse engineering through MCP and CLI for native binaries, applications and runtime behavior.
Open-source agentic reinforcement learning post-training with SGLang rollout and Megatron training.
Build Neo4j knowledge graphs from documents, videos and web pages, then query the data through chat.
Open-source AI browser agent for page questions, browser automation, and reusable workflows.
Compile notes, documents, and transcripts into a self-hosted Markdown wiki with cited answers and MCP access.
Open-source AI CAD workflows for parts, assemblies, circuit boards, manufacturing checks and engineering drawings.
An open-source terminal multiplexer with tiled panes, persistent sessions and a shared inbox for coding agents.
Self-hosted AI assistant with multiple users, specialist agents, persistent memory, and chat integrations.
A local-first research agent workspace for literature reviews, hypotheses, experiments, and research artifacts.
Python library for LLM-based structured text extraction with source grounding and interactive HTML visualization.
Open-source AI video clipping with local rendering, subtitles, covers and publishing copy.
Open-source Kubernetes UI with cluster troubleshooting, live topology, and a built-in MCP server for AI agents.
Open-source tokenization library for encoding and decoding text in research and production.
An open-source development harness for planning, implementing, checking, and reviewing AI-assisted coding tasks.
Cross-platform desktop management for Codex prompts, API providers, sessions, Skills, MCP and configuration files.
Open-source CLI and skills for building, evaluating, and deploying ADK agents on Google Cloud.
Open-source LLM inference with multimodal models, local coding agents, compatible APIs, and Python and Rust SDKs.
Open-source AI pentester that analyzes source code and verifies web application and API vulnerabilities with exploits.
Run coding agents, share their context, and link agent sessions to Git commits in a team timeline.
Open-source AI gateway for model routing, SDK compatibility, request tracing and cost control.
Replace local development port numbers with stable, named .localhost URLs for developers and AI agents.
Open-source container and VM runtime for macOS with Docker compatibility, Kubernetes and isolated AI agent sandboxes.
Open-source Python SDK for robotics data quality checks, multimodal pipelines, and dataset curation.
Run Claude Code, Codex, OpenCode and Pi in isolated workspaces from the web, Slack or an API.
Generate editable parametric 3D models from text or reference images through Codex or Claude Code.
Open-source MCP harness connecting AI assistants to local code and coordinating coding agents.
Local neuro-symbolic memory for offline AI, with verified fact retrieval and an OpenAI-compatible API.
An open-source Hacker News client for article summaries, thread digests, and chat with discussions.
Open-source voice dictation, meeting transcription, and AI assistance with local or cloud models.
Audit Claude Code token usage, diagnose limits, and trace context overhead from local session logs.
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.