MCP servers and skills: search, filter by where they run, and compare.
Routes NVIDIA Nemotron Speech (Formerly Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Open-source auth gateway connecting 1500+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI.
SkillApache-2.0★ 6.0kNo key
Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills befo
OfficialPythonApache-2.0★ 20kNo key
SkillsRegistry by Cognium: discover MCP servers and agent skills with explicit trust and scan-coverage signals. Apache-2.0 SDK and self-hosted node; public read-only MCP endpoint.
SkillApache-2.0★ 4Few starsNo key
NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Shared memory across your team and your AI agents — with judgment about what's worth keeping.
Node.jsApache-2.0★ 82No key
Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or
OfficialHosted by authorApache-2.0★ 1.1kNo key
Instrument any app with OpenTelemetry and ship metrics / logs / traces to Grafana Cloud or self-hosted Mimir / Loki / Tempo / Pyroscope. Covers SDK auto-instrumentation for Go, Java (Grafana JVM agent
OfficialSkillApache-2.0★ 285 in collectionNo key
Give cloud AI agents a real development environment on your own machines.
SkillApache-2.0★ 2.3kNo key
Cairn.ink Memory: lightweight cross-session memory for AI agents, with receipts.
Hosted by authorApache-2.0★ 30No key
Open-source, self-hosted alternative to Composio, Nango, Merge.dev, and Arcade.dev for AI agent integrations. Run GitHub, Slack, Hacker News, and custom HTTP actions over MCP or REST.
SkillApache-2.0★ 842No key
Serve and visually inspect a converted LeRobot dataset in the browser. Use for videos and state/action timelines; do not use for raw workflow HDF5 or incomplete conversion output.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Expand workflow HDF5 demonstrations with action jitter, optionally scoped to node segments. Use for synthetic variants; do not use to collect data, alter state directly, or generate new images.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Replay a workflow HDF5 episode through its original Scene. Use for visual trajectory and recording verification; do not use for policy evaluation or LeRobot data.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Preflight and set up the root-level workflow runtime. Use for installation, missing component environments, or third-party failures; do not use for rollout validation.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Record demonstrations through a workflow's teleop Task into workflow HDF5. Use for keyboard, leader, VR, or bus input; do not use for policy evaluation or autonomous rule-based Tasks.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Run the maintained workflow data-to-policy pipeline from recording through checkpoint validation. Use for full end-to-end requests; do not use for one individual stage.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Observal is self-hosted registry for your coding agent extensions with a built in insight engine. Setup Observal, define the scope and share your Skills, MCPs and Agents with your peers.
PythonApache-2.0★ 4.5kNo key
Convert workflow HDF5 recordings to LeRobot datasets for training or browser inspection. Use for conversion; do not use for replay, augmentation, or raw-data repair.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Orient users to the i4h workflow runtime and route them to the correct stage skill. Use for architecture, support, or where-to-start questions; do not execute a known stage.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Fine-tune a manifest-backed GR00T or openpi remote Task on compatible LeRobot data. Use for training; do not use for inference-only Tasks or checkpoint rollout.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Grade or filter workflow HDF5 episodes with an OpenAI-compatible vision model. Use for visual success labels; do not use for replay, policy evaluation, or recordings without frames.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Who stands behind it
