The agent that grows with you
Python aiai-agentai-agentsanthropicchatgptclaudeclaude-codecodexhermeshermes-agentllmnous-researchopenai
plugin-catalog: hyatlas disclosure fixes from review
Tuna Dev8b968fbd71d7
diff --git a/plugin-catalog/hyatlas.yaml b/plugin-catalog/hyatlas.yamlindex 033ce2c3d99..04077746ad3 100644--- a/plugin-catalog/hyatlas.yaml+++ b/plugin-catalog/hyatlas.yaml@@ -8,7 +8,7 @@ screenshots:- https://raw.githubusercontent.com/tuancookiez-hub/HyAtlas-Memory/386515b75e9fb8a1f6247fc1946d0342b32af9ad/docs/images/desktop-overview.png- https://raw.githubusercontent.com/tuancookiez-hub/HyAtlas-Memory/386515b75e9fb8a1f6247fc1946d0342b32af9ad/docs/images/desktop-graph.pngtitle: HyAtlas Memory-description: "HyAtlas v4 — self-hosted 8-layer memory provider backed by a pure-Go single-binary server you run yourself (chromem-go vectors, in-process BGE-small embeddings, hybrid vector + keyword search, 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 and HYATLAS_LLM_MODEL are set and it has a key (HYATLAS_LLM_KEY, or one handed over by share_llm_key); until then /api/v1/status reports llm \"awaiting_key\". The repo installer pre-fills a free Nous Portal endpoint that Enter accepts, but nothing is sent until a key is supplied. The plugin setting share_llm_key (off by default) supplies one: the plugin asks Hermes for its current Nous Portal key through Hermes's own resolver (resolve_runtime_provider), and only when the server's LLM endpoint is on that key's host does it POST the key to the configured HyAtlas server (default 127.0.0.1:19528) at /api/v1/llm/key, checking every 60 seconds and re-sending every 15 minutes. The server keeps that key in memory only and never writes it to disk. Once configured, each turn's user and assistant text goes to that endpoint (not tool output or context summaries; capped at 12,000 characters). In the default ultra mode the server also sends topic-grouped batches of up to 50 stored facts to it every 6 hours (every 20 minutes while earlier batches are still pending) and supersedes (hides but keeps) the facts the model marks merged or stale, recording a reason for each drop. It also records relations corroborated across turns in the local knowledge graph (HYATLAS_CONSOLIDATE_GRAPH=off disables that). In pro and ultra modes it also sends each owner's open intentions, recent summaries and newest facts to rewrite a short Now page, at most every 15 minutes (HYATLAS_NOW_EVERY), and, after a 30-minute pause in an owner's writes (HYATLAS_EPISODE_GAP; off disables it), up to 40 of that stretch's facts to write one episode summary. HYATLAS_RECONCILE=on (off by default) adds a second LLM call per write that sends the new facts together with similar stored ones so the model can update or replace them; it is meant for a local model. An optional HYATLAS_LLM_FALLBACK_MODEL, tried only when a primary call fails, receives the same text; it is sent the primary key only when it uses the same host. HYATLAS_MODE=lite makes no LLM call. Server endpoints that rewrite stored data are off unless the server runs with HYATLAS_ADMIN=on. The spawned server gets an allowlisted environment (OS essentials plus HYATLAS_*), not the agent's keys. auto_start is off by default; when on, Hermes starts the server as soon as it loads the plugin, and a server started by auto_start or `hermes hyatlas start` keeps running after Hermes exits until `hermes hyatlas stop`. On Windows, if a hyatlas-go.ps1 launcher is configured, `hermes hyatlas start/stop` runs it; the repo's sample launcher points extraction at the Nous Portal and reads no credentials (since 4.8.0 neither it nor the server reads Hermes auth.json). No telemetry."+description: "HyAtlas v4 — self-hosted 8-layer memory provider backed by a pure-Go single-binary server you run yourself (chromem-go vectors, in-process BGE-small embeddings, hybrid vector + keyword search, bitemporal knowledge graph with source citations). Embeddings, the vector index and stored memories are kept locally. 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 are computed locally; stored memories leave the machine only in the LLM calls described below. Extraction is opt-in: the server has no default LLM endpoint and makes no LLM call until HYATLAS_LLM_BASE and HYATLAS_LLM_MODEL are set and it has a key (HYATLAS_LLM_KEY, a file named by HYATLAS_LLM_KEY_FILE, or one handed over by share_llm_key); until then /api/v1/status reports llm \"awaiting_key\". The repo installer pre-fills a free Nous Portal endpoint that Enter accepts, but nothing is sent until a key is supplied. The plugin setting share_llm_key (off by default; the environment variable HYATLAS_SHARE_LLM_KEY=1 also turns it on) supplies one: the plugin asks Hermes for its current Nous Portal key through Hermes's own resolver (resolve_runtime_provider), and only when the server's LLM endpoint is on that key's host does it POST the key over plain HTTP to the configured HyAtlas server (default 127.0.0.1:19528; use it only with a server on the same machine) at /api/v1/llm/key, checking every 60 seconds and re-sending every 15 minutes. The server keeps that key in memory only and never writes it to disk. Once configured, each turn's user and assistant text goes to that endpoint (not tool output or context summaries; capped at 12,000 characters), together with up to 5 related stored facts, 3 entity pages and 5 open intentions of that owner so the model can update them instead of duplicating them. In the default ultra mode the server also sends topic-grouped batches of up to 50 stored facts to it every 6 hours (every 20 minutes while earlier batches are still pending) and supersedes (hides but keeps) the facts the model marks merged or stale, recording a reason for each drop. It also records relations corroborated across turns in the local knowledge graph (HYATLAS_CONSOLIDATE_GRAPH=off disables that). In pro and ultra modes it also sends each owner's open intentions, recent summaries and newest facts to rewrite a short Now page, at most every 15 minutes (HYATLAS_NOW_EVERY), and, after a 30-minute pause in an owner's writes (HYATLAS_EPISODE_GAP; off disables it), up to 40 of that stretch's facts to write one episode summary. HYATLAS_RECONCILE=on (off by default) adds a second LLM call per write that sends the new facts together with similar stored ones (including those under user IDs grouped with the owner by HYATLAS_USER_ALIASES) so the model can update or replace them; it is meant for a local model. An optional HYATLAS_LLM_FALLBACK_MODEL, tried only when a primary call fails, receives the same text; it is sent the primary key only when it uses the same host. HYATLAS_MODE=lite makes no LLM call. Server endpoints that rewrite stored data are off unless the server runs with HYATLAS_ADMIN=on. The spawned server gets an allowlisted environment (OS essentials plus HYATLAS_*), not the agent's keys. auto_start is off by default; when on, Hermes starts the server as soon as it loads the plugin, and a server started by auto_start or `hermes hyatlas start` keeps running after Hermes exits until `hermes hyatlas stop`. On Windows, if a hyatlas-go.ps1 launcher is configured, `hermes hyatlas start/stop` runs it; the repo's sample launcher points extraction at the Nous Portal and reads no credentials (since 4.8.0 it no longer reads Hermes auth.json). The server reads a key file only when HYATLAS_LLM_KEY_FILE is set, live on every call; its docs say not to point that at another program's credentials such as Hermes auth.json. No telemetry."maintainer: tuancookiez-hubtier: communitycategory: memory