Enfold — AI skill for Claude Code
Enfold. Every memory enfolds the whole.
How to install Enfold
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open victorv2i/enfold and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Enfold does
Enfold. Every memory enfolds the whole. Local, private long-term memory for AI agents: one SQLite brain shared by Claude Code, Codex, and Hermes Agent, with hybrid semantic + symbolic recall and gated writes.
Alternatives in AI
- Hindsight — State-of-the-art long-term memory for AI agents by Vectorize 6.7k ★
- Nocturne Memory — A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents 1.3k ★
- Codeseek — Rust-powered code intelligence CLI for AI coding agents 764 ★
README
Enfold
When two agents disagree, you get a conflict you can settle, not a silent guess.
Enfold stores durable facts on your machine, with evidence and history on every claim. When two writers put different values in the same typed slot at equal authority, it opens a conflict, returns a receipt instead of a value, and waits for a human. There is no hosted service. Memory stays local.
The moment
`python -m enfold.demo` (or `enfold demo`) walks that contract on a disposable store. It never opens `~/.hermes/memory_store.db`. Conflict ids change each run. This is a real run on this tree:
Enfold demo
Disposable store. Offline. Local-lexical retrieval.
This is not a bag of notes: current state, conflict, and human resolve are first-class.
1. Client A writes typed state
client: demo-client-a
claim: env:staging.port = 3100
write: outcome=add fact_id=1 authority=0.5
2. Client B writes the same slot at equal authority
client: demo-client-b
claim: env:staging.port = 3200
write: outcome=conflict fact_id=2 authority=0.5
3. Recall returns a conflict receipt, not 3100, not 3200
current facts returned: none
receipt: [conflict:f6a352c0-8976-457e-b57b-e953dddd5bcb slot:env:staging.port members:2 - do not treat either as current]
conflict_id: f6a352c0-8976-457e-b57b-e953dddd5bcb
members: [1, 2]
This is the moment. A competito
Related Skills
Mnemon
Self-hosted, cross-device long-term memory for AI agents via MCP — one vault shared across any MCP client (Cla
Guild
Shared context, memory, and task coordination across AI coding agents. Single Go binary, local SQLite, hybrid
Brain CLI
Persistent memory for AI agents and personal knowledge management. Single-file Python CLI: hybrid semantic + k
Maludb Core
A memory DBMS for long-term institutional memory, human-AI knowledge sharing, and contextual recall. PostgreSQ
Memory Lancedb Pro
Production-grade long-term memory system (v1.1.0-beta.8) for OpenClaw AI agents. Provides persistent, intellig
MultiAgentDocumentAssistant
A multi-agent research paper assistant with durable LangGraph workflows, three-layer long-term memory, hybrid
Related Agents
Web Novel Outline Agent
Outline agent for the Web Novel project type. Produces a three-layer outline (skeleton, volume, chapter) using
Brain Retrieval Engineer
Retrieval engineer — six retrieval strategies (hybrid, graph-enhanced vector, entity-anchored local, guarded T
Integrity Sweep
Read-only mechanical-conservation checker for an academic-writing project in LaTeX. After a restructure, move,