By mistakeknot
Memory synthesis — graduates stable auto-memory facts to AGENTS.md/CLAUDE.md
Memory synthesis for Claude Code.
Claude Code's auto-memory accumulates facts over time, but they live in a flat file that grows without bound. Some of those facts are stable and well-confirmed; others are speculative or stale. intermem graduates the stable ones into curated reference documents (AGENTS.md, CLAUDE.md) and prunes the source.
The pipeline: scan memory files → detect stability (same fact confirmed across multiple sessions via SHA-256 content hashing) → validate citations and paths → deduplicate against existing docs → present for interactive approval → promote to target document + prune from source. A WAL-style journal ensures atomicity: if the process crashes mid-promotion, it recovers cleanly.
First, add the interagency marketplace (one-time setup):
/plugin marketplace add mistakeknot/interagency-marketplace
Then install the plugin:
/plugin install intermem
Run the synthesis pipeline:
/intermem:synthesize
Validate memory health without promoting:
/intermem:validate
intermem/ Python library (scan, stability, validation, dedup, promotion)
skills/ synthesize, validate
.intermem/ Per-project state (metadata.db in SQLite)
.intermem/ must be in .gitignore (local state, not shared)Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub mistakeknot/interagency-marketplace --plugin intermem[DEPRECATED — use intervox] Analyze your writing style and adapt Claude's output to sound like you. Replaced by intervox (via the interim intervoice), which adds a measured stylometric fingerprint, LLMism linter, and verified closed-loop apply on top of the global multi-register profile.
Self-improving agent rig: codifies product and engineering discipline into composable workflows from brainstorm to ship. Compounds knowledge, generates domain agents, monitors its own docs, and surfaces conservative update drift. Orchestrates Claude, Codex, and Oracle through 6 agents, 57 commands, 20 skills, 0 MCP servers. Factory substrate: CXDB turn DAG, scenario bank with satisfaction scoring, evidence pipeline, agent capability policies. Companions: interspect, interphase, interline, interflux, interpath, interwatch, interslack, interform, intercraft, interdev, interpeer, intertest.
Recursive AGENTS.md generator with integrated Oracle critique, CLAUDE.md harmonization, incremental updates, diff previews, and smart monorepo scoping. Cross-AI compatible.
Token efficiency benchmarking, session analytics, and API-equivalent cost analysis for agent workflows
Multi-agent review and research with scored triage, domain detection, content slicing, intermediate finding sharing, and knowledge injection. 17 agents (12 review + 5 research), 8 commands (incl. flux-melange — a goal-seeking adaptive review loop with lens fusion and novelty/risk/taste scoring), 3 skills (flux-engine, flux-review-engine, flux-melange-engine), 2 MCP servers (exa, openrouter-dispatch). Companion plugin for Clavain.
Memory consolidation for Claude Code. Simulates the Auto Dream feature by auditing, deduplicating, and rebuilding your memory files.
Long-term memory for Claude Code — slash commands, skills, opt-in session hooks, codebase indexing, and a deep-retrieval subagent over the @memsy-io/mcp server.
Pure filesystem-based memory system for Claude Code with custom ontology support
Claude Mind - Give Claude photographic memory in ONE portable file. Share, version, and transfer your Claude's brain.
Biomimetic long-term memory for Claude Code with surprisal gating, mutable reconsolidation, affective routing, and sleep consolidation.
Persistent memory for Claude Code — memories survive across sessions, projects, and machines