HN Showcase
Back to browse
GitHub Repository

Tessera — Memory layer for every AI. 58 MCP tools, 54 REST endpoints, local-first, AES-256 encrypted.

14 starsPython

Tessera – MCP server that gives Claude persistent memory and local RAG

by jasonjeong·Mar 7, 2026·3 points·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidNiche GemShip It

Local RAG + MCP for Claude with zero external dependencies—elegant constraint execution.

Strengths
  • •Pure local-first architecture (fastembed + LanceDB) eliminates API costs and privacy concerns
  • •MCP integration feels native; Claude can search automatically without manual context-passing
  • •Incremental re-indexing and knowledge graph visualization show thoughtful design details
Weaknesses
  • •Personal knowledge RAG is a known category; Mem0, Obsidian plugins, and browser extensions solve similar problems
  • •Audience limited to Claude Desktop users with structured document workflows, narrow niche
Target Audience

Claude Desktop users managing large personal knowledge bases or workspace documentation

Similar To

Mem0 · Obsidian · Copilot Chatbot

Similar Projects

Developer Tools●Mid

CogmemAi – Persistent Memory for Claude Code via MCP

Runs extraction and search server-side so your local MCP is a tiny HTTP client — no local DBs, no giant RAM leaks, and an easy npx install and .mcp.json or global MCP registration. It exposes clear tools (save_memory, recall_memories, extract_memories, get_project_context) and adds project-scoped + global preferences — a pragmatic fix for Claude Code's tiny flat-file memory. The tradeoff is obvious: usefulness depends on the hosted API (privacy, uptime, cost), and the repo looks early-stage with minimal commits and docs beyond the quickstart.

Niche GemShip ItSolve My Problem
hifriendbot
203mo ago