Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
open-code-review
SkillsSecure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
git clone https://github.com/alibaba/open-code-review.git -
quivr
AI repositoriesAn open-source engine that turns continuous content streams into search and monitoring. Durable ingestion, hybrid search, alerts, and plugins for formats, models and business rules.
git clone https://github.com/The-Vibe-Company/quivr.git -
Mage-VL-Cowork
Modelsimage text to text model by microsoft · transformers
microsoft/Mage-VL-Cowork -
hybridlog
MCP serversReads your own Garmin mirror: readiness, training load, muscle freshness, and read-only SQL.
ghcr.io/imgrund/hybridlog:0.1.19 -
Spatial clustering 2D grid reconstructor converting OCR boxes into Markdown tables
https://github.com/Alpha-Park/genpark-hybrid-bounding-box-ocr-table-reconstructor-skill/releases/download/v1.0.1/genpark-ocr-table.mcpb -
Hybrid Recursive Ladder
MCP serversAggregate long time-series ranges with a few source requests instead of one per bucket.
hybrid-recursive-ladder-mcp@0.0.8 -
metronix-memory
AI repositoriesSelf-hosted AI agent memory — MCP memory server with durable recall for agents
git clone https://github.com/mtrnix/metronix-memory.git -
minirag-mcp
MCP serversLocal-first RAG MCP server in Python: hybrid search (semantic + BM25 keyword boost) over your own documents. 11 MCP tools + CLI, markitdown ingestion for 12 formats, multilingual embeddings, LanceDB. Nothing leaves your machine.
git clone https://github.com/sfrangulov/minirag-mcp.git -
docsmint
MCP serversOpen-source knowledge base for people and AI agents. Rich-text editing, hybrid search, GraphRAG, and MCP. Self-host with Docker or use DocsMint Cloud.
git clone https://github.com/HiAi-gg/docsmint.git -
supergrep
MCP serversCode search at scale.
git clone https://github.com/infino-ai/supergrep.git -
{ "prompt_type": "Surreal CGI-Photography Hybrid Portrait", "subject": { "reference_identity": "Crucially, the woman's facial features, hair, and unique identity must match the provided reference photo exactly."…
-
eBRBe Hybrid Human + AI Agent Compute Billing
MCP serversTrack human engineering hours plus Claude Code & Cursor compute spend on one client ledger.
-
STRUGGL Hybrid Coach
MCP serversZero-LLM-Math sports science calculators (Hyrox, 1RM/RPE, Zone 2, MEV/MRV) & workout ledger.
-
mcp-local-rag
AI repositoriesLocal-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.
git clone https://github.com/shinpr/mcp-local-rag.git -
flexible-graphrag
MCP serversGraphRAG, RAG, LlamaIndex, LangChain, 15 Prop Graph, 4 RDF, 10 Vector, 3 Search DBs. 14 data srcs, auto sync, Alfresco, Nuxeo, SharePoint, Box, CMIS, S3,GCS,Azure, web. KG auto-bld, Ontologies, 13 LLM providers, Docling, LlamaParse, LiteParse, Hybrid Search, AI Chat. TypeScript React, Vue, Angular, Python, REST, MCP, OpenArch, Langflow, CocoIndex.
git clone https://github.com/stevereiner/flexible-graphrag.git -
Uteke
MCP serversLong-term memory for AI agents: hybrid vector and full-text recall, rooms, time-travel.
-
infino
AI repositoriesEmbedded retrieval library built on Parquet. Fast, efficient, and scalable.
git clone https://github.com/infino-ai/infino.git -
mind-mem
MCP serversPersistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. BM25F + vector hybrid, governance-aware, local-first, zero-infrastructure.
git clone https://github.com/star-ga/mind-mem.git -
You are tasked with reverse-engineering the storytelling approach used by Vox Media to create compelling video content. Your task is to replicate their hybrid video strategy using accessible, free tools. You will: -…
-
Writ
Agents & frameworksGovernance runtime for Claude Code. Enforces workflow gates at tool time, delivers the engineering rules relevant to the work, and preserves decision provenance across sessions.
git clone https://github.com/infinri/Writ.git -
knowledge-rag
AI repositoriesLocal RAG server for Claude Code, Cursor and other MCP clients: hybrid BM25 + vector search with cross-encoder reranking on by default, 13 MCP tools, 33 file types including code, re-indexing on file changes. One Python process with embedded ChromaDB and FastEmbed ONNX: no Docker, database server or API key; offline after the first model download.
git clone https://github.com/lyonzin/knowledge-rag.git -
LodeDB
AI repositoriesWorld's fastest and most compact embedded vector database: exact by default, multimodal, local-first, and GPU-accelerated
git clone https://github.com/Egoist-Machines/LodeDB.git -
Ternary-Bonsai-2-2B-gguf
Modelsimage text to text model by prism-ml · llama.cpp
prism-ml/Ternary-Bonsai-2-2B-gguf -
chatvia
AI repositoriesOpen-source platform for AI chat agents that answer from your own knowledge base. Hybrid RAG search in PostgreSQL, MCP and custom tools, guardrails and human handoff. Put agents on a hosted chat page, a website widget, Slack, Teams, WhatsApp, Telegram or a REST API. Self-host with Docker and open-weight models.
git clone https://github.com/chatvia/chatvia.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.