GitHub Repository

Local-first AI memory with causal graphs. MCP server for Claude Code, Cursor, VS Code, and any MCP client.

1 starsGo

Phloem–Local-first AI memory & causal graphs(MCP server, Zero network)

Name: Phloem–Local-first AI memory & causal graphs(MCP server, Zero network)
Availability: InStock
Author: canopyhq

by canopyhq·Feb 21, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●●●BangerBig BrainZero to OneSolve My Problem

MCP memory standard solves AI context amnesia better than static .claude files.

Strengths

•Semantic search + causal graphs genuinely useful: finds relevant memories by meaning, not keywords, and tracks *why* decisions were made
•MCP standard (not proprietary) means one install unlocks memory for all AI tools—VS Code, Cursor, Claude Code, Windsurf, JetBrains, etc.
•Citations decay confidence automatically when code drifts—memory adapts to refactors instead of hallucinating stale info

Weaknesses

•Requires Go 1.24+, Brew, or binary downloads—setup friction for non-technical users or Windows devs
•Documentation focuses on conceptual 'why' but light on usage examples and troubleshooting

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

204mo ago

Developer Tools●●Solid