Observed Signal · Jun 5, 2026 · Technical Release · Source: DEV Community · Impact: 2/5 · Sentiment: Positive
Nautilus‑Compass v1.1.0 Fixes Memory Recall Consumption Drift
The maintainer of nautilus‑compass published v1.1.0 (June 5, 2026), addressing a class of failures where agent recall surfaced relevant memory metadata but agents did not consume the referenced file bodies. v1.1.0 implements a three-layer fix: embedding the first 800 characters of body text in top recall hits, including lesson bodies in anti‑anchor drift alerts, and a new recall_consumption.py module that detects 'recall fired but not consumed' by scanning session logs. The release also extends the V7 governance plan with a governance_plan MCP tool that routes decomposition phases using platform registries. The package is available via pip and npm, the repo and demo are public, two arXiv papers accompany the work, and the release ran 228 pytests with MIT anchors CC0.
Open-source technical release improves reliability of LLM agent memory recall and consumption; relevant to teams building agentic workflows and automated publishing but not a major platform policy or industry-shifting announcement.
Track arXiv Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- nautilus-compass v1.1.0 released on 2026-06-05.
- v1.1.0 introduces a three-layer fix for 'recall != consumption' (embed body in top-3 hits; embed past-mistake body in anti-anchor alerts; detect unconsumed recalls via recall_consumption.py).
- recall_consumption.py scans live session jsonl files to find recent recall blocks and checks for subsequent Read tool calls; wired into drift_check MCP tool and a mid_session_hook that runs every 25 tool calls with thresholds (nag when ≥3 unconsumed and ratio <0.3).
- v1.1.0 updates the V7 governance plan with a governance_plan MCP tool that reads two registries (_platform_registry/agents_capabilities.json and _platform_registry/anchor_packs_phases.json) to route phase decomposition without code changes.
- Release artifacts: pip and npm packages (nautilus-compass==1.1.0), GitHub repo (github.com/chunxiaoxx/nautilus-compass), Hugging Face demo, two arXiv papers, and 228 passing pytests; license/anchors MIT CC0.
Connected Companies & Entities
5 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Nautilus-Compass v1.1.0 Ships Recall-Consumption Fix
The author released nautilus-compass v1.1.0, a technical update to their agent memory system that addresses a class of failures where recalled memory items were surfaced but not actually consumed by LLM agents. The release implements a three-layer fix: (v0) embed the first ~800 characters of body text in the top-3 recall hits, (v1) include past-mistake bodies inside 'anti-anchor' drift alerts, and (v2) introduce recall_consumption.py to detect recall-fired-but-not-consumed signatures by checking session logs for subsequent Read tool calls. The release also extends governance tooling (governance_plan MCP tool) to route phases via platform registries (agents_capabilities.json and anchor_packs_phases.json). The repo provides pip/npm packages, links to demos and two arXiv papers, and retains prior evaluation numbers while improving consumption behavior in live sessions.
Codex Forgetful Plugin Released for Forgetful Memory MCP
A developer published an open-source Codex plugin that integrates with the Forgetful Memory MCP (a configurable memory framework) to provide opinionated workflows for agent context and session memory management. The plugin adds skills for memory curation, context gathering (including optional Context7 integration), project initiation and an encode-repo workflow that converts repositories into atomic notes for persistent agent memory. The author reports anecdotal model comparisons—favoring GPT 5.5 over Anthropic’s Opus 4.7 for this hands-off use case—and notes the plugin currently omits automatic memory-curation hooks in favor of manual slash-command workflows. The post and GitHub repo were published on 2026-05-10.
Neonmem 0.9.7 Released with Offline Vector Recall
Neonmem 0.9.7 is a technical release that introduces a two-level importer separating a deduplicated, searchable facts pool from typed memories extracted from agent chats. The release replaces the previous embedder with IBM Granite-30M run as a fused fp16 ONNX graph via ONNX Runtime, enabling FAISS-based retrieval on CPU without GPUs, cloud services, or third‑party LLMs. New features include tag canonicalization, deduplicated chat capture, a single compressed "cartridge" containing the full source corpus, and opt-in AES-256-GCM encryption at rest. The build is distributed as Windows (signed installer + portable) and Linux (AppImage) binaries, with macOS support forthcoming. All core components are open-source / permissively licensed.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.