AI and memory

Turn-level governance observability for Claude Code transcripts. Local-first, no LLM inside.

MCP server for Langfuse LLM observability — trace and observation analysis.

Local-first persistent memory for AI coding agents.

Post-tx outcome verification via LLM-as-judge. Zero Core Verify.

MCP server for Tessera's LLM cost-optimization layer: anchored spend, drift, recommendations.

Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP.

Dubstrata: Causal Financial & Narrative CDN providing Graph RAG & Deep Research Reports

x402-gated semantic vector cache for agent swarms: Redis-backed similarity lookup. Paid in USDC.

Zero-knowledge persistent memory for Claude — encrypted, semantic search, EU hosted.

Parse partial / truncated / messy JSON for LLM tool calls and structured outputs.

PLATEAU 3D city data as scene-editing and glTF export tools for creative LLM agents.

RAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch.

Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.

Persistent session memory for Claude Code. Local SQLite, no LLMs, no network.

Inject, parse, and strip [N] citation markers in RAG outputs.

Cross-LLM persistent memory: store context once, recall it from any AI model.

9-LLM consensus + disagreement scoring + cheapest-route picks to fight hallucinations.

URL to LLM-ready markdown — plus per-page category, page_structure, and query-driven highlights.

Portable agent memory anchored on Solana. Local SQLite + vector recall, open export.

Replicate MCP server - image, video, audio, speech, LLM, vision, upscale, 3D, training. 36 tools.

Provable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).

Durable causal memory for AI agents — semantic recall, causal lineage, and skills. Local-first.

Search the Federal Register, read & diff CFR sections, query Regulations.gov. Any LLM supported.

Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth