MCP servers and skills: search, filter by where they run, and compare.
Local ASR on your hardware | 本地部署语音识别：Qwen3-ASR / FunASR, audio & video transcription, speakers, subtitles and independent sound analysis. Docker · HTTP · CLI · MCP · Agent Skill.
PythonApache-2.0★ 1Few starsNo key
Offline semantic search across files, PDFs, and photos. Describe what you need; nothing leaves your machine.
PythonMITFew starsNo key
Agent skill and CLI for narrated talking-head explainer videos: script, voice edit with re-transcription checks, HeyGen avatar, subtitles
SkillMIT★ 1Few starsNo key
Local songwriting tools with your own soft rhyme rules. English lyrics, pinned Qwen3.5-9B, CLI/Python/MCP.
PythonGPL-3.0★ 1Few starsNo key
A voice-native decision model. Ask your audio about what was said, how it was said, and who said it.
PythonApache-2.0★ 2Few starsNo key
Copy or cut conversation context between Codex, Pi, DSH, OpenCode, Qwen, Claude and WorkBuddy. Local CLI + skill with native session index cleanup.
SkillMIT★ 6No key
Run LLM eval suites, cache every call, and compare two runs item by item against a noise floor. CLI and MCP server.
PythonMITFew starsNo key
A coding agent built from scratch (no framework) that fixes failing tests in a locked-down Docker sandbox. Benchmark of validated bugs injected into toolz and boltons; structured tools beat bash-only
PythonMITFew starsNo key
Experimental gateway for MCP tool calls: information-flow labels, a content tracker, session rules, human approval, audit. Research prototype; synthetic data; same-author evaluation.
PythonMITFew starsNo key
Modular Multi-MCP & Hybrid RAG AI framework for local & frontier models. Connect Python tools, query knowledge graphs, and inspect agent traces with a build-in inspector.
PythonMIT★ 1Few starsNo key
Voice-first Alexa+ agent layer: a standards-compliant MCP server (2025-11-25, Streamable HTTP) with approval-gated real-world and coding tools
PythonMITFew starsNo key
An AI agent that turns natural language questions into reproducible, independently validated simulation experiments.
PythonMIT★ 4Few starsNo key
OpenAPI spec in, chaos test harness out: WireMock stubs, contract tests and failure scenarios from a team of local LLM agents.
PythonMIT★ 2Few starsNo key
Open-source video generator for Shorts and long-form. Free and local.
PythonMIT★ 2Few starsNo key
Stateless MCP 2026-07-28 server + evaluation of LLM tool selection at scale (N=5..100, embedding retrieval) and agent loop guards on a local LLM
PythonMITFew starsNo key
OpenAI-compatible Python SDK + MCP server for 110+ Chinese frontier AI models (DeepSeek, Qwen, GLM, Kimi, Seedance) via NovAI. Zero platform fee.
PythonMITFew starsNo key
Semantic code search for Claude Code: search functions by meaning via LLM-written summaries; returns pointers, never code. MCP server + plugin.
PythonMITFew starsNo key
🛰️ Self-contained, obliterated AI agent on your own GPU. Zero cloud, zero filters: reads your docs, runs tools, ask anything "ANYTHINGG!!" and serves your whole crew via vLLM Or AON-MCP
PythonMITFew starsNo key
One command tells you why your local AI stack is slow or broken: unloaded Ollama models, VRAM held by something else, offline or relayed tailnet peers. Graded findings, typed fixes, MCP server.
PythonMITFew starsNo key
MCP server for Data, AI and cloud tech watch, with local LLM digests (Ollama)
PythonMITFew starsNo key
Two open-weight AIs fight over your agent: one attacks it, one heals it, until it's battle-tested.
SkillLink only★ 1Few stars
Find where your agent breaks before your users do. Seeded tool-use tasks checked by code, on your own tools.
PythonMIT★ 2Few starsNo key
AI course assessment
SkillGPL-3.0★ 2Few starsNo key
An AI guard for your Frigate cameras: alerts that explain themselves, memory that learns from one-tap corrections, models on your own hardware.
PythonMIT★ 2Few starsNo key
Who stands behind it
