discover · compare · collections · requirements · contribute · feed · watching · stats · help with your tokens
raphasouthall/neurostack
Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection, session harvesting into memories. Local-first.
History and source changes · Reports and owner responses · Compare
Similar
- logseq/logseq
A privacy-first, open-source platform for knowledge management and collaboration. Download link: http://github.com/logseq/logseq/releases. roadmap: https://logseq.io/p/NX4mc_ggEV
Why this match
topics knowledge-base, knowledge-graph, local-first; language differs: Python → Clojure; license differs: Apache-2.0 → AGPL-3.0
- zycaskevin/Vault-Agent-Memory
Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.
Why this match
topics knowledge-base, local-first, mcp
- dodo-labs-ai/mem-forge
Give every agent your team's brain on day one. The memory layer for AI agents. Everything your team knows. Cited, and always up to date.
Why this match
topics knowledge-base, mcp, mcp-server
- memvid/memvid
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
Why this match
topics knowledge-base, knowledge-graph, python; language differs: Python → Rust
- codexu/note-gen
Capture first. Organize later. A local-first Markdown app that turns scattered records into clear notes with AI.
Why this match
topics knowledge-base, local-first, markdown; language differs: Python → TypeScript; license differs: Apache-2.0 → GPL-3.0
- 398894496-arch/KRouter
Your coding agents remember what you decided — and what you changed. Plain-Markdown memory in Obsidian, shared by Claude Code, Codex and Cursor over MCP. Every answer cites its page; when the vault does not know, it says so. Imports your past sessions on install.
Why this match
topics knowledge-base, mcp, mcp-server; license differs: Apache-2.0 → MIT
- modelcontextprotocol/python-sdk
The official Python SDK for Model Context Protocol servers and clients
Why this match
topics mcp, mcp-server, python; license differs: Apache-2.0 → MIT
- remete618/widemem-ai
Local-first memory layer for LLM apps and agents. Runs offline on Ollama, sentence-transformers and FAISS; OpenAI and Anthropic optional. Importance scoring, contradiction resolution, confidence-aware retrieval.
Why this match
topics ai-memory, local-first, mcp