Public catalog
24 tools. No owner fields. No holdings.
Imported from Crew's saved_tool export. Search name, tags, summary. Private notes, owner IDs, and AppSumo state never shipped. Pair a tool with a launch stack, a replace lander, or a best open-source roundup.
24 matches · page 1 of 1
- service ClawHub ClawHub — a fast skill registry for agents, with vector search.
- repository cognee Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
- repository engram Engram is a hybrid long-term memory plugin for OpenClaw agents. It stores structured facts in SQLite with FTS5 full-text search and semantic vectors in LanceDB, generating embeddings via OpenAI models, and exposes memory_store/memory_recall tools plus an engram CLI.
- repository geolens GeoLens is a self-hosted, open-source spatial data hub for GIS and data teams. It ingests vector and raster data, indexes catalog metadata with pg_trgm fuzzy search and optional pgvector semantic search, serves OGC API Features/Records and STAC endpoints, and includes a browser map builder.
- repository graphify Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
- service HelixDB HelixDB is the graph-vector database for AI memory — knowledge graphs, vectors, temporal, and full-text search in one Rust engine for agent memory, RAG, and company brains.
- product LatticeDB Single-file embedded property-graph database with native vector search, BM25 full-text search, durable streams, and graph changefeeds.
- product Milvus Open-source cloud-native vector database for ANN search. Apache-2.0; self-host it, or use the managed offering as Zilliz Cloud. Written in Go and C++.
- repository mnemosyne Mnemosyne is a local-first AI memory layer for agents, backed by a single SQLite database with one pure-Python dependency. It exposes an MCP server, Python SDK, and CLI, and integrates with Hermes, Claude Code, Cursor, Codex, Windsurf, OpenWebUI, and OpenClaw.
- repository onyx Onyx is an open-source (MIT for the Community Edition) AI chat platform that connects to major LLM providers and adds RAG, agents, web search, code execution, and enterprise search via indexing connectors. It can be self-hosted in a lightweight Lite mode or a full Standard deployment.
- repository OpenKB OpenKB is an open-source CLI that compiles documents (PDF, Word, Markdown, URLs, and more) into a wiki-style knowledge base using LLMs, powered by PageIndex's vectorless, tree-based retrieval for long documents. It supports querying, chat, skill generation, and an optional bundled web UI.
- repository PageIndex 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
- service Pageindex Ai PageIndex is a vectorless, reasoning-based RAG engine that mirrors how humans read documents. Achieve 98.7% accuracy on FinanceBench with traceable, explainable retrieval.
- product pgvector Open-source vector similarity search for Postgres. Store embeddings next to relational data and query with SQL. Runs on any Postgres, including Supabase, Neon, and a VPS you operate.
- product Pinecone Managed vector database for RAG and agents. Starter is free (2 GB, 1 million read units). Builder is $20/month flat. Standard has a $50 minimum, storage $0.33/GB-month, and read units $16–$18 per million.
- product Qdrant Open-source vector search engine with a managed cloud. Cloud Free is a 0.5 vCPU / 1 GB RAM / 4 GB disk cluster (about 1 million 768-dimension vectors). Standard is usage-based on vCPU, RAM, and disk. Apache-2.0 engine you can also self-host.
- product spaCy · Industrial-strength Natural Language Processing in Python spaCy is a free open-source library for Natural Language Processing in Python. It features NER, POS tagging, dependency parsing, word vectors and more.
- service SurrealDB SurrealDB is a database and an agent memory layer. Documents, graphs, vectors, and SQL in one engine - and context for your AI agents wherever your data lives.
- product turbopuffer Object-storage-backed vector search. Launch plan minimum is $16/month. Queries are billed at $1/PB with a 1.28 GB minimum per query. Storage and write unit rates are on usage, with the Launch floor covering small bills.
- repository turbovec A vector index built on TurboQuant, written in Rust with Python bindings
- repository utopia World's first open-source enterprise world model.
- product Weaviate Open-source vector database with a managed cloud. Cloud Free holds 100,000 objects. Flex starts at $45/month with dimension rates from $0.00465 per million and storage from $0.12/GiB.
- repository WeKnora Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
- product Zilliz Cloud Managed Milvus vector database. Dedicated Performance and Capacity CUs are $0.273/CU-hour; storage is $0.025/GB-month. A Capacity CU holds about 8 million 768-dimension vectors.