“Agent memory”

Use this skill when storing or retrieving per-agent operational memory in a two-channel SQLite model (longterm + shortterm) with a single slow-context blob.

Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking

Manage durable working-session memory for coding agents.

Build Anvia agents and tools — Agent options, tool definitions, approvals, memory, streaming, multi-agent teams, and provider wiring.

What to examine during a reflection pass and how to write observations to memory/{agent}/needs.md.

Read-only MCP bridge for alethech — verifiable, Ed25519-signed agent memory over stdio.

This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent…

Recall and retain useful, non-sensitive project knowledge in Hindsight.

Save successful action tips as soon as they work and retrieve them for later actions under matching observable conditions; distill reusable procedures into…

Save what was done in this session to the shared agent memory (log entry + project page update) so any other agent or harness can pick it up later.

Local persistent memory for AI agents: SQLite + FTS5 (BM25) lexical search, zero external infra.

Local-first governed MCP memory backend for coding agents.

Role-persona CLI for managing AI agent identity, memory, and knowledge systems.

Lineage-gated agent memory tools on Postgres + pgvector, enforced by row-level security.

Token-lean memory for AI agents: a knowledge graph searched cheaply.

Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens.

Open-source causal memory for AI agents: persistent, explainable, MCP-native memory (13 tools).

Event-sourced, auditable agent memory over MCP: cited checkout, replayable provenance.

Use when persisting knowledge, recording findings, capturing ideas, or recalling what was previously learned.

Gives AI agents persistent memory across conversations using Honcho.

Periodic evidence-based self-audit of the whole agent system — the orchestrator, its docs/SSOTs, rules, memory, subagents, tools, infra and the work it claims…

Intelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.

Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code…

A meta-skill that establishes a 'One Brain' portable memory folder (.agent/).