The agent that grows with you
Python aiai-agentai-agentsanthropicchatgptclaudeclaude-codecodexhermeshermes-agentllmnous-researchopenai
catalog: limbic 0.7.1 — supersession + calibration + Windows support
D Yiapanisa1c9d2ac3adb
diff --git a/plugin-catalog/limbic.yaml b/plugin-catalog/limbic.yamlindex bcd6f9d56ca..e44fde1da5a 100644--- a/plugin-catalog/limbic.yaml+++ b/plugin-catalog/limbic.yaml@@ -1,16 +1,16 @@name: limbicrepo: https://github.com/dyiapanis/limbic-sha: cddf94dfbac5598a451af9110ac56e15111fe16a-description: "Self-organising memory provider (MemoryProvider ABC): local SQLite (WAL) with sqlite-vec KNN + FTS5 hybrid recall, adaptive trust scoring, activation maturation, interference-based forgetting, NLI-based correction detection and synaptic atrophy. No LLM cost — all lifecycle mechanisms are deterministic. The optional inline chat recall indicator is off by default (recall_indicator in limbic.yaml) and memory injection works identically either way. Recall is confidence-gated: when nothing clears the calibration floor, recall abstains (no_confident_match) instead of surfacing near-misses, and the agent answers from what it knows without attributing anything to memory. Tools (remember/recall) and lifecycle hooks dispatch via the MemoryManager from the registered provider — this entry registers a MemoryProvider only, so provides_tools/provides_hooks are empty. Disclosure — on first primary session start downloads ~1.0GB of ONNX models (Arctic Embed 2.0 L int8 embedding, ~570MB; MiniLMv2 NLI, ~430MB, on first contradiction check) from huggingface.co at pinned commits with hash checks into ~/.cache/limbic/ (outside HERMES_HOME); at every model load, every file in those cache folders that is not in the pinned manifest is deleted — including unrelated files if you point embedding/nli cache_dir at a shared folder — which reclaims stale orphans from prior versions (e.g. an older fp32 cache of ~2.2GB); the memory database is never touched; spaCy NER models are not downloaded and must be installed manually for entity extraction; memory stays local in limbic.db under HERMES_HOME, and hermes backup adds VACUUM snapshots under HERMES_HOME/backups; no telemetry. Stores created or reindexed on 0.6.0+ record the embedder that produced their vectors and report stale_embedder=true after an embedder change until `hermes limbic reindex`; stores from 0.5.x keep serving their fp32 vectors unflagged until reindexed. PolyForm Noncommercial 1.0.0 (commercial use requires a separate license)."+sha: 898346568e3bfc511587521dad9e0ff594995461+description: "Self-organising memory provider (MemoryProvider ABC): local SQLite (WAL) with sqlite-vec KNN + FTS5 hybrid recall, adaptive trust scoring, activation maturation, interference-based forgetting, NLI-based correction detection and synaptic atrophy. No LLM cost — all lifecycle mechanisms are deterministic. The optional inline chat recall indicator is off by default (recall_indicator in limbic.yaml) and memory injection works identically either way. Recall is confidence-gated: when nothing clears the calibration floor, recall abstains (no_confident_match) instead of surfacing near-misses, and the agent answers from what it knows without attributing anything to memory. Tools (remember/recall) and lifecycle hooks dispatch via the MemoryManager from the registered provider — this entry registers a MemoryProvider only, so provides_tools/provides_hooks are empty. Disclosure — on first primary session start downloads ~1.0GB of ONNX models (Arctic Embed 2.0 L int8 embedding, ~570MB; MiniLMv2 NLI, ~430MB, on first contradiction check) from huggingface.co at pinned commits with hash checks into ~/.cache/limbic/ (outside HERMES_HOME); at every model load, every file in those cache folders that is not in the pinned manifest is deleted — including unrelated files if you point embedding/nli cache_dir at a shared folder — which reclaims stale orphans from prior versions (e.g. an older fp32 cache of ~2.2GB); the memory database is never touched; spaCy NER models are optional and install via `hermes limbic languages --set <lang>` (entity extraction stays disabled without one); memory stays local in limbic.db under HERMES_HOME, and hermes backup adds VACUUM snapshots under HERMES_HOME/backups; no telemetry. Stores created or reindexed on 0.6.0+ record the embedder that produced their vectors and report stale_embedder=true after an embedder change until `hermes limbic reindex`; stores from 0.5.x keep serving their fp32 vectors unflagged until reindexed. Since 0.7.0: supersession is enforced at recall (when a correction and the fact it contradicts both match a query, only the correction surfaces; safety-valved so a below-floor correction never hides the old fact), the NLI pair-check gate opens one band lower for correction-cued writes, the recall confidence floor is calibrated at 0.50, and trust adaptation requires at least 10 signals / 5 maturity observations before any parameter shifts. Since 0.7.1: CI-tested on Linux and Windows; on Windows the store initialises lock-free (cross-process file locks are POSIX-only) and the model cache lives under %USERPROFILE%\\.cache\\limbic. PolyForm Noncommercial 1.0.0 (commercial use requires a separate license)."maintainer: dyiapanistier: communitycategory: memoryrequires_hermes: ">=0.21.4"docs_url: https://github.com/dyiapanis/limbic#readme-version: "0.6.4"-image: https://raw.githubusercontent.com/dyiapanis/limbic/cddf94dfbac5598a451af9110ac56e15111fe16a/assets/banner.png+version: "0.7.1"+image: https://raw.githubusercontent.com/dyiapanis/limbic/898346568e3bfc511587521dad9e0ff594995461/assets/banner.pngreadme: true-platforms: []+platforms: [linux, windows]capabilities:provides_tools: []provides_hooks: []