THOUGHT — Temporal Hierarchical Object Union & Graph Hybrid Toolkit. A local MCP memory server with bi-temporal graph + vector + temporal layers, a query router, and a consolidation engine.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"thought-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# THOUGHT [](https://pypi.org/project/thought-mcp/) [](https://pypi.org/project/thought-mcp/) [](LICENSE) [](https://github.com/RNBBarrett/thought-mcp/actions/workflows/ci.yml) [](https://github.com/RNBBarrett/thought-mcp/actions/workflows/docker.yml) [](https://github.com/RNBBarrett/thought-mcp/pkgs/container/thought-mcp) [](#status--contributions) [](CONTRIBUTING.md) **T**emporal **H**ierarchical **O**bject **U**nion & **G**raph **H**ybrid **T**oolkit — a local MCP memory server that gives any LLM a persistent, auditable memory fabric on your own machine. > OB1 stores your thoughts. Karpathy's wiki compiles your knowledge. **THOUGHT** remembers with provenance, understands relationships, detects contradictions, never forgets what used to be true — and routes every query to the right mathematical structure before touching a single byte of data. ### Status & contributions **THOUGHT is experimental software.** Expect rough edges, surface changes between minor versions, and the occasional sharp corner — especially in the v0.4 query layer and local-LLM paths. APIs that the README documents are stable enough to build against, but anything described as a "subset" or marked "v0.4+" is still settling. **The project aims to improve on existing context / memory systems** for LLM agents. The closest comparables are Mem0, Letta/MemGPT, Zep, and Graphiti — each shipped impressive work; THOU…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.