poc-memory

A persistent memory system for AI assistants. Stores knowledge as a weighted graph of nodes and relations, with automatic recall via Claude Code hooks.

Quick start

# Install
cargo install --path .

# Initialize the store
poc-memory init

# Install Claude Code hooks and systemd service
poc-memory daemon install

Configuration

Config file: ~/.config/poc-memory/config.toml

# Names used in transcripts and agent prompts
user_name = "Alice"
assistant_name = "MyAssistant"

# Where memory data lives (store, logs, episodic digests)
data_dir = "~/.claude/memory"

# Where Claude Code session transcripts are stored
projects_dir = "~/.claude/projects"

# Nodes that should never be decayed (comma-separated)
core_nodes = "identity.md, preferences.md"

# Journal settings for session-start context loading
journal_days = 7
journal_max = 20

# Context groups loaded at session start, in order.
# Each [context.NAME] section specifies a group of nodes to load.
# If no "label" is given, the section name is used (underscores become spaces).
[context.identity]
keys = "identity.md"

[context.people]
keys = "alice.md, bob.md"

[context.technical]
keys = "project-notes.md, architecture.md"

# Orientation loaded last — current task state, not deep identity
[context.orientation]
keys = "where-am-i.md"

Override the config path with POC_MEMORY_CONFIG=/path/to/config.toml.

Commands

Core operations

poc-memory init                    # Initialize empty store
poc-memory search QUERY            # Search nodes (1-3 words, AND logic)
poc-memory render KEY              # Output a node's content
poc-memory write KEY < content     # Upsert a node from stdin
poc-memory delete KEY              # Soft-delete a node
poc-memory rename OLD NEW          # Rename a node (preserves UUID/edges)
poc-memory categorize KEY CAT      # Set category: core/tech/gen/obs/task

Journal

poc-memory journal-write "text"    # Write a journal entry
poc-memory journal-tail [N]        # Show last N entries (default 20)
poc-memory journal-tail N --full   # Show full content (not truncated)

Feedback loop

poc-memory used KEY                # Mark a recalled node as useful (boosts weight)
poc-memory wrong KEY [CONTEXT]     # Mark a node as wrong (reduces weight)
poc-memory gap DESCRIPTION         # Record a knowledge gap for later filling

Graph operations

poc-memory link N                  # Interactive graph walk from a node
poc-memory graph                   # Show graph statistics
poc-memory status                  # Store overview: node/edge counts, categories

Maintenance

poc-memory decay                   # Apply weight decay to all nodes
poc-memory consolidate-session     # Guided 6-step memory consolidation

Context loading (used by hooks)

poc-memory load-context            # Output full session-start context

This loads all context groups from the config file in order, followed by recent journal entries. The memory-search hook binary calls this automatically on session start.

Daemon

poc-memory daemon                  # Run the background daemon
poc-memory daemon install          # Install systemd service + Claude hooks

The daemon watches for completed Claude sessions and runs experience mining and fact extraction on transcripts.

Mining (used by daemon)

poc-memory experience-mine PATH    # Extract experiences from a transcript
poc-memory fact-mine-store PATH    # Extract facts and store them

How the hooks work

The memory-search binary is a Claude Code UserPromptSubmit hook. On each prompt it:

1. First prompt of a session: Runs poc-memory load-context to inject full memory context (identity, reflections, journal, orientation).
2. Post-compaction: Detects context compaction and reloads full context.
3. Every prompt: Extracts keywords and searches the store for relevant memories. Deduplicates against previously shown results for the session.

Session state (cookies, seen-keys) is tracked in /tmp/claude-memory-search/ and cleaned up after 24 hours.

Architecture

• Store: Append-only Cap'n Proto log (nodes.capnp, relations.capnp) with in-memory cache. Nodes have UUIDs, versions, weights, categories, and spaced-repetition intervals.
• Graph: Nodes connected by typed relations (link, auto, derived). Community detection and clustering coefficients computed on demand.
• Search: TF-IDF weighted keyword search over node content.
• Decay: Exponential weight decay with category-specific factors. Core nodes decay slowest; observations decay fastest.
• Daemon: Uses jobkit for task scheduling with resource-gated LLM access (one slot by default to manage API costs).

For AI assistants

If you're an AI assistant using this system, here's what matters:

• Search before creating: Always poc-memory search before writing new nodes to avoid duplicates.
• Close the feedback loop: When recalled memories shaped your response, call poc-memory used KEY. When a memory was wrong, call poc-memory wrong KEY. This trains the weight system.
• Journal is the river, topic nodes are the delta: Write experiences to the journal. During consolidation, pull themes into topic nodes.
• Config tells you who you are: poc-memory reads your name from the config file. Agent prompts use these names instead of generic "the user" / "the assistant".