AI and memory

Local, privacy-first document catalogue for AI agents: metadata-only discovery, no cloud, no RAG.

Local-first AI memory over MCP. No account; you own the store.

On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.

Memory MCP server for Claude Code. Correct a fact and the old version stops being recalled.

Agent memory where every fact carries a receipt, and deletion is provable.

Deterministic engineering solvers: biquad filter design, room eigenmodes, LLM VRAM fit.

Knowledge-graph memory for your team's documents. Answers cite the source, not a summary.

Agentic AI runtime: persistent memory, vault, autonomous agents, deep research, DeFi execution.

Force evidence-gated, tiered claim reporting (FACT/INFERENCE/SPECULATION). No-LLM.

LLM pricing where every rate carries its source and the date it was last confirmed.

Exact document sections on demand for LLM agents: index in context, search, read, grep, neighbours.

Local-first agent memory over SQLite: remember, recall, link, forget. Degrades, never fails.

Local-first RAG MCP server: hybrid search over a folder of your own documents

Verification and memory layer for coding-agent workflows.

LLM-maintained personal wiki: cross-references sources, flags contradictions. Local markdown.

Knowledge-lifecycle MCP: turn agent work into memory, recall it across projects, promote to org.

Persistent memory with contradiction detection, burnout monitoring, and 69 intelligence tools.

Narrow code retrieval for agents: outlines, symbol context, dep graph, persistent memory.

Analyze LLM API costs: token waste detection, caching savings estimates, model comparison

Spec-driven dev workflow MCP: start_* orchestration, memory, GitNexus, quality gates.

Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values.

Local-first operational pulses, durable ticket memory, and governed connection discovery.

Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM

Memory for AI agents that tracks beliefs over time and surfaces contradictions