Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By mistakeknot
Cross-session semantic cache for Claude Code. Content-addressed blob storage, per-project manifests, and session tracking — reduces cold start time and eliminates redundant file reads across sessions.
npx claudepluginhub mistakeknot/interagency-marketplace --plugin intercacheCross-session semantic cache for Claude Code.
intercache stores and retrieves file content across Claude Code sessions using content-addressed blob storage. When Claude reads a file that hasn't changed since last session, the cached version loads instantly instead of re-reading from disk. Session tracking records which files are accessed, so future sessions can pre-warm the most relevant files.
Files are stored by SHA256 hash with 2-character prefix sharding, so identical content is never stored twice. Per-project manifests track mtime and size for fast invalidation without re-hashing.
intercache is an internal plugin in the Demarch monorepo. Install from the interagency marketplace:
/plugin marketplace add mistakeknot/interagency-marketplace
/plugin install intercache
| Tool | Purpose |
|---|---|
cache_lookup | Return cached content if file unchanged |
cache_store | Store file content with SHA256 dedup |
cache_invalidate | Invalidate by path, pattern, or project |
cache_warm | Pre-warm cache from recent sessions |
cache_stats | Hit rates, sizes, file counts |
session_track | Record file accesses for cross-session dedup |
session_diff | Compare accesses between sessions |
cache_purge | Wipe cached data (per-project or global) |
src/intercache/
server.py MCP server (8 tools)
store.py Content-addressed blob store (SHA256, 2-char prefix sharding)
manifest.py Per-project file manifest (SQLite, mtime+size validation)
session.py Session tracking (JSONL read logs, cross-session dedup)
hooks/
post-commit.sh Git hook for cache invalidation on commit
scripts/
launch-intercache.sh MCP server launcher
All data stored at ~/.intercache/:
blobs/ — Content-addressed blob storeindex/<project-hash>/ — Per-project manifests and session logsEmbedding tools (embedding_index, embedding_query) moved to intersearch, which provides persistent vector storage with the nomic-embed-text-v1.5 model. intercache now focuses exclusively on file caching and session tracking.
Admin access level
Server config contains admin-level keywords
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Persistent memory for Claude Code. Capture work across sessions and recall relevant context.
Automatic CORE memory search and ingest plugin for Claude Code
Persistent local memory for Claude Code. Cross-session recall with vector search, automatic archiving, zero cloud dependencies.
Persistent memory system for Claude Code with SQLite, FTS5, and vector search
Persistent memory system for Claude Code - seamlessly preserve context across sessions
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.
[DEPRECATED — use intervoice] Analyze your writing style and adapt Claude's output to sound like you. Replaced by intervoice, which reads one global multi-register profile instead of per-project glob-routed files.
Recursive AGENTS.md generator with integrated Oracle critique, CLAUDE.md harmonization, incremental updates, diff previews, and smart monorepo scoping. Cross-AI compatible.
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, 52 commands, 19 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.
Token-efficient code reconnaissance for LLMs. Autonomous skills save 48-85% tokens via diff-context, semantic search, structural patterns, and symbol analysis. Includes MCP server for direct tool integration.
Token efficiency benchmarking, session analytics, and API-equivalent cost analysis for agent workflows
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim