Instructions for AEndrix03/Graft, a project described as: Local-first semantic cache for AI agents. A small C daemon + CLI that remembers what your agent learned across sessions. Plugs into Claude Code, Codex, Gemini CLI, and Claude Desktop / ChatGPT via MCP. No LLM calls, no SaaS, no API key.
11 8d agonot scanned
tokens not measured
originalApache-2.0
MCP server "graft" as configured in AEndrix03/Graft. Runs C:/personal/Graft/integrations/mcp-server/server.py with python. Needs 1 environment variable to run.
One-shot configurator that wires graft into a CLAUDE.md (global or project-local) so the agent uses the persistent memory consistently in every session. Asks the user 4 short questions (scope, caching, retrieve strategy, save strategy), then writes a … block into the chosen CLAUDE.md. Triggered by /graft-init…
Persistent graph memory across conversations. The master skill — search BEFORE answering non-trivial questions, save AFTER solving non-obvious ones. Three companion skills handle the heavy lifting: /memoryze (save with smart granularity), /recall (escalating search query→retrieve→explore), /memory-audit (read-only…
Batch knowledge ingestion from external sources (a folder, a codebase, a docs tree, a set of files). Plans the ingestion as a list of well-shaped nodes with reconciled keywords, shows the user the plan for approval, then executes idempotently. Triggered by /learn, "ingest this folder into memory", "porta questo codice…
Health check + maintenance audit of the graft graph. Reports hit rate, hoarding ratio, top reused nodes, never-reused nodes, stale entries, and similar-but-separate clusters that may be duplicates. Suggests concrete actions (re-save with a better title, promote to README, drop stale, narrow over-broad nodes) but does…
Distill the current conversation (or a specified excerpt) into N high-quality graft nodes and save them. Triggered by /memoryze, "save this to memory", "ricorda questo", "memorize this", or whenever the user explicitly wants the agent to commit knowledge to the persistent graph. The user can hint at granularity…
Smart graft search that picks the right tool (query → retrieve → explore) based on the question's shape, escalates when results are weak, and presents findings ranked by confidence with the originating evidence. Triggered by /recall, "do we have something about X", "have we seen this before", "ricordi se", "search the…