AI and memory

LLM prices on OpenRouter now and since 2023: history, drops, cheapest model for a job. No API keys.

Read, measure and explain LLM eval runs of a digline suite. Cannot promote a baseline.

Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation

Sizes a training job before it launches: peak memory, smallest GPU, max batch, cost.

Shared memory for Claude Code, Codex, Cursor, Gemini CLI and more, kept verbatim on your own PC.

Scans LLM/agent code for Unbounded Consumption / denial-of-wallet risks (OWASP LLM Top 10 2026 #6)

Persistent local memory for MCP-compatible AI coding agents, stored per repository in SQLite.

Open, local-first engram memory for AI agents: read, correct, delete; shared over MCP.

Whole Wicked suite for agents: market data, SEC filings, wallet checks, risk, identity, memory.

Self-hosted MCP memory for AI agents: persistent context with evidence-backed claims.

Self-hosted, uncensored AI agent: ask it tasks, search its long-term memory and your documents.

One memory for every AI: Claude, ChatGPT and more share a memory that lives on your computer.

Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.

Memory for AI agent teams across tools, sessions, repositories, and teammates.

Local memory and context retrieval for AI agents through CueMap.

Memory that knows when a remembered fact has been replaced, not just when it was written.

Persistent memory for AI coding agents: one Rust binary, one local SQLite database.

Open-source AI context firewall for governed model, retrieval, memory, and tool access.

Encrypted, local memory for Claude, Codex/ChatGPT and Copilot. Needs the free Vitkilabs Anvil app.

Cut your Claude Code bill, measured on your own sessions. Profile and slim any LLM conversation.

MindQL queries, hybrid search, and a thought graph - read/write memory for AI agents.

PowerPoint (.pptx) MCP server: editable vector diagrams, tables, budgeted reads, render-to-verify

Inspectable, correctable project memory in git-versioned Markdown for AI agents.

Scans RAG content/scraped pages for indirect prompt injection