Skip to main content

​
Intelligence Layer

The Intelligence Layer uses LLMs and advanced algorithms to keep your memory store healthy, your retrieval sharp, and your agents onboarded faster.

​
Entity & Relationship Extraction

Reads raw text — conversations, logs, documents, decision traces, and memory entries — and pulls out the entities in it (services, people, tools, infrastructure) along with how they relate to each other. An LLM does the extraction; the results are stored with confidence scores, temporal validity, and a link back to the trace they came from, which is what populates the knowledge graph. Six relation types are recognised: Extraction runs on demand. To have it run automatically as traces arrive, set AMFS_AUTO_EXTRACT=true on the server.

​
Memory Critic

Automated quality analyzer that scans the memory store and detects five issue classes:
  • Toxic — repeated negative correlations
  • Stale — entries not referenced in a long time
  • Contradictory — conflicting entries for the same key
  • Uncalibrated — confidence scores misaligned with outcome history
  • Orphaned — entries with no links to any outcome or other entries

​
Memory Distiller

Compacts a large store into a smaller, higher-quality one. The amfs_distill tool generates a bootstrap set — the entries a new agent should start from, so it inherits the useful parts of an existing brain without loading the whole history. Pruning and consolidation of near-duplicates are handled separately by memory consolidation.

​
Memory Safety Validator

Checks a candidate memory before you commit to it: contradictions against what is already stored, temporal consistency, and confidence thresholds. Deletions are additionally checked for causal chain integrity, so you do not remove an entry that a recorded decision still depends on.
This is a tool you call, not a gate that runs on every write. amfs_write does not validate — call amfs_validate first when you want a candidate checked. Validation returns findings; it never blocks a write on your behalf.

​
Multi-Strategy Retrieval

Combines semantic, BM25 keyword, temporal, and confidence signals via Reciprocal Rank Fusion, weighted 0.4 / 0.2 / 0.2 / 0.2 by default. Once a learned ranking model has been trained it joins the pipeline with 30% of the weight, and the other strategies rebalance to make room for it.

​
Pro MCP Tools