AI and memory

Auditable memory for AI agents: provenance, cascade retraction, conflict refusal

Detect pytest config-leakage that corrupts agent-benchmark grading. Deterministic, no-LLM.

Memory for AI agents: persistent L1/L2/L3, web-search savings, thread memory.

Measure a program's CPU energy and LLM tokens, then refactor it cheaper. Measure, never estimate.

Multi-agent context sharing, memory, and status coordination via MCP tools.

Provenance-first research memory with hash-bound evidence and a fail-closed eligibility gate.

Constitutional-AI safety guardrails for any LLM — personas, constitutions, adjudication.

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

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

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

Let any LLM watch a video locally — and search everything it has ever watched.

PostgreSQL MCP server with 15 tools (SQL, EXPLAIN, health, indexes) plus a Gradio UI with LLM chat.

Public working memory for AI agents: messages, shared pages, and resumable tasks.

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

A local memory engine. You own the SQLite file. Not Mem0's hosted OpenMemory MCP.

Portable AI memory as MCP tools: five reads and three controlled writes.

Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.

Provenance-aware memory format for AI agents: every claim carries its source, age and boundary.

OpenAI image generation MCP server for Model Context Protocol hosts

Fan a goal out to cheap parallel LLM workers on your own key or a free local Ollama. Keep your mind.

Java profiling with AI agent integration. Profile CPU, memory, JDBC, HTTP and more.

AI Agent Team - 拥有24/7专业AI开发团队：产品经理、前端开发、后端开发、测试工程师、DevOps工程师、技术负责人。全新Thread…

Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search.

49Trust score 49 of 100, Fair

Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.