tuancookiez-hub

HyAtlas v4 — self-hosted 7-layer memory provider backed by a pure-Go single-binary server you run yourself (chromem-go vectors, in-process BGE-small embeddings, bitemporal knowledge graph with source citations). Embeddings, the vector index and stored memories stay local. Ships agent tools (hyatlas_status/search/recent/add), a `hermes hyatlas` CLI, a Desktop pane with a starmap graph view, and a web dashboard. Disclosure — requires the separate hyatlas-go server, installed by the user. The plugin never downloads or bundles it, and it talks only to the configured server (default 127.0.0.1:19528). Embeddings and stored memories stay local. Extraction is opt-in: the server has no default LLM endpoint and makes no LLM call until HYATLAS_LLM_BASE, HYATLAS_LLM_MODEL and HYATLAS_LLM_KEY are all set. The repo installer pre-fills a free Nous Portal endpoint that Enter accepts, but nothing is sent until you also enter a key. Once configured, each turn, including that turn's tool output, goes to that endpoint. In the default ultra mode the server also sends batches of up to 200 stored facts to it every 6 hours and deletes the facts the model marks merged or stale. HYATLAS_MODE=lite makes no LLM call. The spawned server gets an allowlisted environment (OS essentials plus HYATLAS_*), not the agent's keys. auto_start is off by default. On Windows, if a hyatlas-go.ps1 launcher is configured or sits beside the binary, `hermes hyatlas start/stop` runs it; the repo's sample launcher reads your Nous token from Hermes auth.json and points extraction at the Nous Portal. No telemetry.