Back to browse
GitHub Repository

Persistent reasoning graph for AI memory — tracks what was decided, not just what was said

3 starsPython

Cairn – Event-sourced reasoning graphs for AI memory

by smcady·Mar 20, 2026·2 points·0 comments

AI Analysis

●●●BangerBig BrainWizardry

Tracks what you decided, not just what you said — propositions with confidence scores and lifecycle status.

Strengths
  • Typed graph structure captures contradictions and refinements, not flat vector embeddings.
  • MCP server integration means zero code changes to existing Claude Code workflows.
  • Local fastembed embeddings by default, optional Voyage AI upgrade for quality.
Weaknesses
  • AI memory is a crowded category — Mem0, LangChain, and others already exist.
  • Requires Claude Code specifically; no generic LLM integration yet.
Category
Target Audience

AI developers and heavy Claude Code users

Similar To

Mem0 · LangChain Memory · Aider

Similar Projects

Developer Tools●●●Banger

FlowScript – Agent memory where contradictions are features

Five queries vector stores can't answer: why(), tensions(), blocked(), whatIf(), alternatives().

Big BrainZero to OneWizardry
phillipclapham
212mo ago
AI/ML●●Solid

Kremis – Deterministic memory graph for AI agents (Rust)

Deterministic graph memory vs. embeddings is clever, but fragmentation of AI memory ecosystems is already painful.

Big BrainWizardry
M2Dr3g0n
104mo ago
AI/ML●●Solid

Graph-based memory for local LLMs with multi-hop not just vector search

Knowledge graph traces beat vector similarity for multi-hop reasoning queries.

Big BrainDark Horse
Chrisszz
401mo ago