nexo-brain 1.7.0 → 2.1.0

package/README.md

@@ -6,7 +6,7 @@
 [![GitHub stars](https://img.shields.io/github/stars/wazionapps/nexo?style=social)](https://github.com/wazionapps/nexo/stargazers)
 [![License: AGPL-3.0](https://img.shields.io/badge/License-AGPL--3.0-blue.svg)](https://www.gnu.org/licenses/agpl-3.0)
 
-> The first AI memory system with architectural inhibitory control — the agent reasons about whether to act before acting. Cognitive Cortex, Context Continuity via auto-compaction hooks, Smart Startup, Context Packets, Auto-Prime, and 30 Core Rules as DNA. Battle-tested from 6 months of production use, validated via multi-AI debate.
+> The first AI memory system with architectural inhibitory control — the agent reasons about whether to act before acting. Cognitive Cortex, Context Continuity via auto-compaction hooks, Smart Startup, Context Packets, Auto-Prime, 30 Core Rules as DNA, auto-update, auto-diary, and CLAUDE.md version tracker. Battle-tested from 6 months of production use, validated via multi-AI debate.
 
 **NEXO Brain transforms any MCP-compatible AI agent from a stateless assistant into a cognitive partner that remembers, learns, forgets, adapts, and builds a relationship with you over time.**
 
@@ -198,7 +198,7 @@ This means long sessions (8+ hours) feel like one continuous conversation instea
 
 ## Cognitive Features
 
-NEXO Brain provides 29 cognitive tools on top of the 78 base tools, totaling **115+ MCP tools**. These features implement cognitive science concepts that go beyond basic memory:
+NEXO Brain provides **147+ MCP tools** across 20+ categories. These features implement cognitive science concepts that go beyond basic memory:
 
 ### Input Pipeline
 
@@ -267,29 +267,89 @@ NEXO Brain was evaluated on [LoCoMo](https://github.com/snap-research/locomo) (A
 
 Full results in [`benchmarks/locomo/results/`](benchmarks/locomo/results/).
 
-## Nervous System (v1.6.0)
+## Nervous System (v2.0.0)
 
-NEXO Brain doesn't just respond — it runs autonomous processes in the background, like a biological nervous system. 11 scripts handle maintenance, health monitoring, and self-improvement without any user interaction:
+NEXO Brain doesn't just respond — it runs 15 autonomous processes in the background, like a biological nervous system. They handle maintenance, health monitoring, and self-improvement without any user interaction:
 
 | Script | Schedule | What It Does |
 |--------|----------|-------------|
 | **cognitive-decay** | 03:00 daily | Ebbinghaus decay + memory consolidation + duplicate merging + dreaming |
-| **deep-sleep** | 04:30 daily | Reads full session transcripts, finds uncaptured corrections and protocol violations |
-| **daily-self-audit** | 07:00 daily | Health checks, guard stats, trust score review, metrics |
+| **sleep** | 04:00 daily | Synaptic pruning, expired data cleanup |
+| **deep-sleep** | 04:30 daily | 4-phase overnight pipeline: Collect→Extract→Synthesize→Apply. Analyzes all sessions, detects emotional patterns, abandoned projects, productivity issues, and auto-creates learnings |
+| **self-audit** | 07:00 daily | Health checks, guard stats, trust score review, metrics |
+| **postmortem** | 23:30 daily | Session consolidation, extract patterns from day's events |
 | **catchup** | On boot | Runs any missed scheduled processes (Mac was off/asleep) |
-| **evolution-run** | Weekly | Self-improvement proposals — NEXO suggests and applies enhancements |
-| **followup-hygiene** | Weekly | Normalizes statuses, flags stale followups, cleans orphans |
-| **immune** | 04:00 daily | Quarantine processing, memory promotion/rejection, synaptic pruning |
-| **watchdog** | Every 30 min | Monitors 15+ services, LaunchAgents, and infrastructure health |
-| **github-monitor** | 08:00 daily | Checks issues, PRs, and commits on public repos |
-| **learning-validator** | Nightly | Validates learnings for staleness, contradictions, and duplicates |
-| **cognitive-migrate** | On upgrade | Schema migrations for cognitive.db — safe, reversible evolution |
+| **tcc-approve** | On boot (macOS) | Auto-approve macOS permissions for Claude Code updates |
+| **prevent-sleep** | Always (daemon) | Keeps machine awake for nocturnal processes (caffeinate/systemd-inhibit) |
+| **evolution** | Weekly (Sun) | Self-improvement proposals — NEXO suggests and applies enhancements |
+| **followup-hygiene** | Weekly (Sun) | Normalizes statuses, flags stale followups, cleans orphans |
+| **immune** | Every 30 min | Quarantine processing, memory promotion/rejection, synaptic pruning |
+| **synthesis** | Every 2 hours | Memory synthesis — discovers cross-memory patterns |
+| **backup** | Every hour | SQLite database backups |
+| **watchdog** | Every 5 min | Monitors services, LaunchAgents, and infrastructure health |
+| **auto-close-sessions** | Every 5 min | Cleans stale sessions |
 
-All scripts run via macOS LaunchAgents (or catch-up on Linux). If your Mac was asleep during a scheduled process, the catch-up script re-runs everything in order when it wakes.
+All processes are defined in `src/crons/manifest.json` and auto-synced to your system by `nexo_update`. On macOS they run via LaunchAgents; on Linux via systemd user timers (or crontab fallback). Personal crons (your own scripts) are never touched by the sync. If your Mac was asleep during a scheduled process, the catch-up script re-runs everything in order when it wakes.
 
-### LaunchAgent Templates
+## Deep Sleep v2 — Overnight Learning (v2.1.0)
 
-13 macOS automation templates are included for scheduling the nervous system. The installer configures them automatically. On Linux, equivalent cron entries are generated.
+Deep Sleep is a 4-phase pipeline that runs at 4:30 AM and makes NEXO smarter while you sleep:
+
+```
+Phase 1: COLLECT (Python)
+├── Reads all session transcripts from the day
+├── Splits each session into individual .txt files
+└── Gathers DB state (followups, learnings, trust)
+
+Phase 2: EXTRACT (Opus, one call per session)
+├── 8 types of findings per session:
+│   ├── Uncaptured corrections (user corrected agent, no learning saved)
+│   ├── Self-corrected errors (knowledge gaps to fix)
+│   ├── Unformalised ideas (mentioned but never tracked)
+│   ├── Missed commitments (promised but no followup)
+│   ├── Protocol violations (guard_check, heartbeat, change_log)
+│   ├── Emotional signals (frustration, flow, satisfaction)
+│   ├── Abandoned projects (started but not finished)
+│   └── Productivity patterns (corrections, proactivity, tool efficiency)
+└── Outputs per-session JSON with findings + emotional timeline
+
+Phase 3: SYNTHESIZE (Opus, one call)
+├── Cross-session patterns (same error in 5 sessions = systemic)
+├── Daily mood arc with score (0.0 = terrible day, 1.0 = great day)
+├── Recurring triggers (what causes frustration vs flow)
+├── Productivity analysis (corrections, tool efficiency)
+├── Abandoned project detection
+├── Morning agenda (prioritized)
+└── Calibration recommendations
+
+Phase 4: APPLY (Python)
+├── Auto-creates learnings from high-confidence findings
+├── Creates followups for unfinished work
+├── Updates mood_history in calibration.json (30-day rolling)
+├── Generates session-tone.json (emotional guidance for next session)
+└── Writes morning-briefing.md
+```
+
+### Session Tone — Emotional Intelligence
+
+Deep Sleep generates a `session-tone.json` that tells NEXO how to behave next morning:
+
+- **Agent made many mistakes yesterday** → Acknowledge them, show what was learned, demonstrate improvement
+- **User had a bad day (mood < 40%)** → Supportive approach, lighter start, avoid known frustration triggers
+- **User had a great day (mood > 70%)** → Reinforce momentum, reference wins, push ambitious goals
+- **Agent was too reactive** → Be proactive today, don't wait for instructions
+
+This is read by `nexo_smart_startup` and injected into every session's context. NEXO adapts its personality based on real behavioral data, not just configuration.
+
+## Cron Manifest (v2.1.0)
+
+All core crons are defined in `src/crons/manifest.json`. When you run `nexo_update`, the sync script:
+- **Installs** new crons from the manifest
+- **Updates** changed schedules/intervals
+- **Removes** crons no longer in the manifest (only core ones)
+- **Never touches** personal crons you created yourself
+
+Run `python3 src/crons/sync.py --dry-run` to preview changes without applying.
 
 ## Dashboard (v1.6.0)
 
@@ -312,18 +372,17 @@ Memory alone doesn't make a co-operator. What makes the difference is the **beha
 
 ### Automated Hooks
 
-8 hooks fire automatically at key moments in every Claude Code session:
+7 hooks fire automatically at key moments in every Claude Code session:
 
 | Hook | When | What It Does |
 |------|------|-------------|
-| **SessionStart** | Session opens | Generates briefing from SQLite: overdue reminders, today's tasks, pending followups, active sessions. Cleans up post-mortem flags. |
+| **SessionStart (timestamp)** | Session opens | Writes session timestamp for staleness detection |
+| **SessionStart (briefing)** | Session opens | Generates briefing from SQLite: overdue reminders, today's tasks, pending followups, active sessions. Cleans up post-mortem flags. |
 | **Stop** | Session ends | Mandatory post-mortem: self-critique (5 questions), session buffer entry, followup creation, proactive seeds for next session |
-| **PostToolUse** | After each tool call | Captures meaningful mutations to the Sensory Register + inter-terminal inbox delivery |
-| **PreCompact** | Before context compression | Saves full session checkpoint to SQLite — task, files, decisions, errors, reasoning thread |
+| **PostToolUse (capture)** | After each tool call | Captures meaningful mutations to the Sensory Register + auto-diary every 10 tool calls |
+| **PostToolUse (inbox)** | After each tool call | Inter-terminal inbox delivery between parallel sessions |
+| **PreCompact** | Before context compression | Saves full session checkpoint to SQLite — task, files, decisions, errors, reasoning thread + emergency diary |
 | **PostCompact** | After context compression | Re-injects Core Memory Block so the session continues seamlessly from where it left off |
-| **PreToolUse** | Before tool execution | Validates tool parameters and injects guard context for destructive operations |
-| **Notification** | External events | Routes incoming notifications (GitHub, email, watchdog alerts) to the active session |
-| **Caffeinate** | Always (optional) | Keeps Mac awake for nocturnal cognitive processes |
 
 ### The Session Lifecycle
 
@@ -367,15 +426,10 @@ Existing users upgrading from any previous version:
 npx nexo-brain  # detects current version, migrates automatically
 ```
 - Updates hooks, core files, plugins, scripts, and LaunchAgent templates
-- Runs `cognitive-migrate.py` for safe, reversible schema evolution
+- Runs database schema migrations automatically
 - **Never touches your data** (memories, learnings, preferences)
 - Saves updated CLAUDE.md as reference (doesn't overwrite customizations)
 
-For manual migration (e.g., from a custom setup):
-```bash
-python3 ~/.nexo/scripts/nexo-cognitive-migrate.py
-```
-
 ## Knowledge Graph (v0.8)
 
 A bi-temporal entity-relationship graph with 988 nodes and 896 edges. Entities and relationships carry both valid-time (when the fact was true) and system-time (when it was recorded), enabling temporal queries like "what did we know about X last Tuesday?". BFS traversal discovers multi-hop connections between concepts. Event-sourced edges with smart dedup (ADD/UPDATE/NOOP) prevent redundant writes while preserving full history.
@@ -425,8 +479,7 @@ The installer handles everything:
     - Node.js project detected
   Configuring MCP server...
   Setting up nervous system...
-    11 autonomous scripts configured.
-    13 LaunchAgent templates installed.
+    15 autonomous processes configured.
     Dashboard configured at localhost:6174.
   Caffeinate enabled.
   Generating operator instructions...
@@ -457,26 +510,42 @@ That's it. No need to run `claude` manually. Your operator will greet you immedi
 | Component | What | Where |
 |-----------|------|-------|
 | Cognitive engine | Python: fastembed, numpy, vector search | pip packages |
-| MCP server | 111+ tools for memory, cognition, learning, guard | ~/.nexo/ |
-| Plugins | Guard, episodic memory, cognitive memory, entities, preferences | ~/.nexo/plugins/ |
-| Hooks (8) | SessionStart, Stop, PostToolUse, PreCompact, PostCompact, PreToolUse, Notification, Caffeinate | ~/.nexo/hooks/ |
-| Nervous system | 11 autonomous scripts (decay, sleep, audit, evolution, watchdog, etc.) | ~/.nexo/scripts/ |
-| Dashboard | Web UI at localhost:6174 (6 pages) | ~/.nexo/dashboard/ |
+| MCP server | 147+ tools for memory, cognition, learning, guard | NEXO_HOME/ |
+| Plugins | Guard, episodic memory, cognitive memory, entities, preferences, update, etc. | Code: src/plugins/, Personal: NEXO_HOME/plugins/ |
+| Hooks (7) | SessionStart, Stop, PostToolUse, PreCompact, PostCompact | NEXO_HOME/hooks/ |
+| Nervous system | 15 autonomous processes (decay, sleep, audit, evolution, watchdog, etc.) | NEXO_HOME/scripts/ |
+| Dashboard | Web UI at localhost:6174 (6 pages) | NEXO_HOME/dashboard/ |
 | CLAUDE.md | Complete operator instructions (Codex, hooks, guard, trust, memory) | ~/.claude/CLAUDE.md |
-| LaunchAgents | 13 templates for macOS automation | ~/Library/LaunchAgents/ |
-| Auto-update | Checks for new versions at boot | Built into catch-up |
-| Claude Code config | MCP server + 8 hooks registered | ~/.claude/settings.json |
+| Schedule config | schedule.json with customizable process times and timezone | NEXO_HOME/config/ |
+| Auto-update | Non-blocking startup check (5s max), opt-out via schedule.json | Built into server startup |
+| CLAUDE.md tracker | Version-tracked core sections with safe updates preserving customizations | Built into auto-update |
+| Auto-diary | 3-layer system: PostToolUse every 10 calls, PreCompact emergency, heartbeat DIARY_OVERDUE | Built into hooks |
+| Claude Code config | MCP server + 7 hooks + 15 processes registered | ~/.claude/settings.json |
 
 ### Requirements
 
 - **macOS or Linux** (Windows via [WSL](https://learn.microsoft.com/en-us/windows/wsl/install))
 - **Node.js 18+** (for the installer)
-- **Claude Opus (latest version) strongly recommended.** NEXO Brain provides 111+ MCP tools across 20 categories. This cognitive load requires a top-tier model with large context window. Smaller models (Haiku, Sonnet) may struggle with tool selection and produce inconsistent results. Opus handles all 111+ tools without hesitation.
+- **Claude Opus (latest version) strongly recommended.** NEXO Brain provides 147+ MCP tools across 20+ categories. This cognitive load requires a top-tier model with large context window. Smaller models (Haiku, Sonnet) may struggle with tool selection and produce inconsistent results. Opus handles all 147+ tools without hesitation.
 - Python 3, Homebrew, and Claude Code are installed automatically if missing.
 
 ## Architecture
 
-### 111+ MCP Tools across 20 Categories
+### Unified Code/Data Separation (v2.0.0)
+
+NEXO Brain separates **code** (immutable, in the repo or npm package) from **data** (personal, in `NEXO_HOME`):
+
+| Path | Contents |
+|------|----------|
+| `src/` (or npm package) | Server, plugins, hooks, scripts — never modified at runtime |
+| `NEXO_HOME/` (default `~/.nexo/`) | Database, config, personal plugins, schedule, backups |
+| `NEXO_HOME/config/schedule.json` | Customizable process schedules, timezone, auto_update flag |
+| `NEXO_HOME/plugins/` | Personal plugins that override or extend repo plugins |
+| `NEXO_HOME/data/` | SQLite databases (nexo.db, cognitive.db), migration state |
+
+The plugin loader scans `src/plugins/` first (base), then `NEXO_HOME/plugins/` (personal override by filename). This dual-directory approach lets you extend NEXO without forking the repo.
+
+### 147+ MCP Tools across 20+ Categories
 
 | Category | Count | Tools | Purpose |
 |----------|-------|-------|---------|
@@ -490,7 +559,7 @@ That's it. No need to run `claude` manually. Your operator will greet you immedi
 | Reminders | 5 | list, create, update, complete, delete | User's tasks and deadlines |
 | Followups | 4 | create, update, complete, delete | System's autonomous verification tasks |
 | Learnings | 5 | add, search, update, delete, list | Error patterns and prevention rules |
-| Credentials | 5 | create, get, update, delete, list | Secure local credential storage |
+| Credentials | 5 | create, get, update, delete, list | Local credential storage (plaintext SQLite — protect with filesystem permissions) |
 | Task History | 3 | log, list, frequency | Execution tracking and overdue alerts |
 | Menu | 1 | menu | Operations center with box-drawing UI |
 | Entities | 5 | search, create, update, delete, list | People, services, URLs |
@@ -501,10 +570,11 @@ That's it. No need to run `claude` manually. Your operator will greet you immedi
 | Adaptive & Somatic | 4 | adaptive_weights, adaptive_override, somatic_check, somatic_stats | Learned signal weights + pain memory per file |
 | Knowledge Graph | 4 | kg_query, kg_path, kg_neighbors, kg_stats | Bi-temporal entity-relationship graph |
 | Context Continuity | 2 | checkpoint_save, checkpoint_read | Auto-compaction session preservation |
+| Update | 1 | update | Pull latest code, backup, migrate, verify (with rollback) |
 
 ### Plugin System
 
-NEXO Brain supports hot-loadable plugins. Drop a `.py` file in `~/.nexo/plugins/`:
+NEXO Brain supports hot-loadable plugins with a dual-directory loader. Base plugins live in `src/plugins/` (repo). Personal plugins go in `NEXO_HOME/plugins/` and can override base plugins by filename. Drop a `.py` file in `NEXO_HOME/plugins/`:
 
 ```python
 # my_plugin.py
@@ -524,7 +594,7 @@ Reload without restarting: `nexo_plugin_load("my_plugin.py")`
 - **Everything stays local.** All data in `~/.nexo/`, never uploaded anywhere.
 - **No telemetry.** No analytics. No phone-home.
 - **No cloud dependencies.** Vector search runs on CPU (fastembed), not an API.
-- **Auto-update is opt-in.** Checks GitHub releases, never sends data.
+- **Auto-update is resilient.** NEXO checks for updates on startup. If an update fails, it continues with the current version and notifies you. Local migrations (database schema, configuration) always run. Network updates (git pull) can be disabled by setting `auto_update: false` in `NEXO_HOME/config/schedule.json`.
 - **Secret redaction.** API keys and tokens are stripped before they ever reach memory storage.
 
 ## The Psychology Behind NEXO Brain
@@ -558,7 +628,7 @@ NEXO Brain is designed as an MCP server. Claude Code is the primary supported cl
 npx nexo-brain
 ```
 
-All 111+ tools are available immediately after installation. The installer configures Claude Code's `~/.claude/settings.json` automatically.
+All 147+ tools are available immediately after installation. The installer configures Claude Code's `~/.claude/settings.json` automatically.
 
 ### OpenClaw
 
@@ -574,7 +644,7 @@ Add NEXO Brain to your OpenClaw config at `~/.openclaw/openclaw.json`:
     "servers": {
       "nexo-brain": {
         "command": "python3",
-        "args": ["~/.nexo/src/server.py"],
+        "args": ["~/.nexo/server.py"],
         "env": {
           "NEXO_HOME": "~/.nexo"
         }
@@ -587,7 +657,7 @@ Add NEXO Brain to your OpenClaw config at `~/.openclaw/openclaw.json`:
 Or via CLI:
 
 ```bash
-openclaw mcp set nexo-brain '{"command":"python3","args":["~/.nexo/src/server.py"],"env":{"NEXO_HOME":"~/.nexo"}}'
+openclaw mcp set nexo-brain '{"command":"python3","args":["~/.nexo/server.py"],"env":{"NEXO_HOME":"~/.nexo"}}'
 openclaw gateway restart
 ```
 
@@ -617,7 +687,7 @@ This replaces OpenClaw's default memory system with NEXO Brain's full cognitive
 
 ### Any MCP Client
 
-NEXO Brain works with any application that supports the MCP protocol. Configure it as an MCP server pointing to `~/.nexo/src/server.py`.
+NEXO Brain works with any application that supports the MCP protocol. Configure it as an MCP server pointing to `server.py` in the code directory, with `NEXO_HOME` env var set.
 
 ## Listed On
 
@@ -637,11 +707,11 @@ NEXO Brain builds on ideas from several open-source projects. We're grateful for
 
 | Project | Inspired Features |
 |---------|------------------|
-| [Vestige](https://github.com/pchaganti/gx-vestige) | HyDE query expansion, spreading activation, prediction error gating, memory dreaming, prospective memory |
-| [ShieldCortex](https://github.com/PShieldCortex/ShieldCortex) | Security pipeline (4-layer memory poisoning defense) |
-| [Bicameral](https://github.com/nicobailey/Bicameral) | Quarantine queue (trust promotion policy for new facts) |
-| [claude-mem](https://github.com/nicobailey/claude-mem) | Hook auto-capture (extracting decisions and facts from conversations) |
-| [ClawMem](https://github.com/nicobailey/ClawMem) | Co-activation reinforcement (memories retrieved together strengthen connections) |
+| Vestige | HyDE query expansion, spreading activation, prediction error gating, memory dreaming, prospective memory |
+| ShieldCortex | Security pipeline (4-layer memory poisoning defense) |
+| Bicameral | Quarantine queue (trust promotion policy for new facts) |
+| claude-mem | Hook auto-capture (extracting decisions and facts from conversations) |
+| ClawMem | Co-activation reinforcement (memories retrieved together strengthen connections) |
 
 ## Support the Project
 
@@ -654,15 +724,45 @@ If NEXO Brain is useful to you, consider:
 
 [![Star History Chart](https://api.star-history.com/svg?repos=wazionapps/nexo&type=Date)](https://star-history.com/#wazionapps/nexo&Date)
 
+## Known Issues (v2.0.0)
+
+| Priority | Issue | Planned |
+|----------|-------|---------|
+| P0 | Credentials stored in plaintext SQLite — protect with filesystem permissions | v2.1.0 |
+| P0 | Shell hooks use SQL string interpolation (injection risk) | v2.1.0 |
+| P0 | Dashboard has no authentication (localhost only) | v2.1.0 |
+| P0 | Database migrations are fail-open (errors logged but not blocking) | v2.1.0 |
+
 ## Changelog
 
+### v2.0.0 — Unified Architecture (2026-03-31)
+- **Code/data separation**: Code in repo (`src/`), personal data in `NEXO_HOME` (default `~/.nexo/`). `NEXO_HOME` env var required.
+- **Plugin loader dual-directory**: Scans `src/plugins/` (base) then `NEXO_HOME/plugins/` (personal override by filename).
+- **Auto-update on startup**: Non-blocking (5s max), resilient, opt-out via `schedule.json`. Separate from manual `nexo_update` tool.
+- **Auto-diary**: 3-layer system — PostToolUse every 10 calls, PreCompact emergency save, heartbeat DIARY_OVERDUE signal.
+- **CLAUDE.md version tracker**: Section markers enable safe core updates without losing user customizations.
+- **schedule.json**: Customizable process schedules with timezone support and `auto_update` flag.
+- **15 autonomous processes**: Added auto-close-sessions, synthesis, backup, tcc-approve, prevent-sleep (cross-platform).
+- **7 hooks**: SessionStart (timestamp + briefing), Stop, PostToolUse (capture + inbox), PreCompact, PostCompact.
+- **147+ MCP tools**: Added `nexo_update` tool for manual updates with rollback.
+- **Lambda fix**: Decay values were 24x too aggressive (STM: 7h to 7d, LTM: 2.4d to 60d).
+- **Guard scoping**: Was returning 35+ irrelevant blocking rules; now scoped to area and gated to high/critical.
+- **12 rounds of external audit**: ~60 findings resolved.
+
+### v1.7.0 — Full Internationalization + Linux Support (2026-03-31)
+- **Full i18n**: All UI strings, error messages, DB status values in English. NLP detection patterns retain bilingual keywords (Spanish + English) for multilingual user support.
+- **Linux support**: systemd user timers (preferred) or crontab fallback for all automated cognitive processes.
+- **Auto-resolve followups**: Change log entries automatically cross-reference and complete matching open followups.
+- **Free-form learning categories**: No more hardcoded category validation — use any category name.
+- **CLAUDE.md template rewrite**: 494 to 127 lines, compact procedural format with full heartbeat signal reactions.
+- **Complete sanitization**: All hardcoded paths use `NEXO_HOME` env var. Zero personal data in the repo.
+
 ### v1.6.0 — Nervous System + Dashboard v2 (2026-03-30)
-- **Nervous System**: 11 autonomous scripts (decay, deep sleep, self-audit, catchup, evolution, followup hygiene, immune, watchdog, github monitor, learning validator, cognitive migrate)
+- **Nervous System**: 11 autonomous scripts (decay, deep sleep, self-audit, catchup, evolution, followup hygiene, immune, watchdog, github monitor, learning validator)
 - **Dashboard v2**: 6 interactive pages at localhost:6174 (Overview, Graph, Memory, Somatic, Adaptive, Sessions)
-- **LaunchAgent Templates**: 13 macOS automation templates included in the package for scheduling the nervous system
-- **Migration Script**: `cognitive-migrate.py` for safe, reversible schema evolution on upgrades
-- **Hooks**: 8 total — added PreToolUse (parameter validation + guard injection) and Notification (external event routing)
-- **Installer**: Now configures dashboard LaunchAgent, nervous system scripts, and all 13 templates automatically
+- **LaunchAgent Templates**: macOS automation templates included in the package for scheduling the nervous system
+- **Hooks**: 7 total — SessionStart, Stop, PostToolUse, PreCompact, PostCompact
+- **Installer**: Now configures dashboard LaunchAgent, nervous system scripts, and all templates automatically
 
 ### v1.5.2 — Deep Sleep (2026-03-29)
 - **Deep Sleep**: Reads full session transcripts (not just diary) — finds uncaptured corrections, protocol violations, missed commitments
@@ -718,7 +818,7 @@ If NEXO Brain is useful to you, consider:
 - New tools: `nexo_checkpoint_save`, `nexo_checkpoint_read`
 - Heartbeat automatically maintains checkpoint every interaction
 - Core Memory Block re-injected post-compaction with task, files, decisions, reasoning thread
-- 115+ total tools, 20 categories
+- 115+ total tools at the time, 20 categories
 
 ### v1.0.0 — Cognitive Cortex + Stable Release (2026-03-26)
 - **Cognitive Cortex**: architectural inhibitory control (ASK/PROPOSE/ACT modes)
@@ -735,7 +835,7 @@ If NEXO Brain is useful to you, consider:
 
 ### v0.9.0 — Cognitive Memory (2026-03-15)
 - Atkinson-Shiffrin memory model (STM → LTM promotion)
-- Semantic RAG with fastembed (BAAI/bge-small-en-v1.5, 384 dims)
+- Semantic RAG with fastembed (BAAI/bge-base-en-v1.5, 768 dims)
 - Trust scoring, sentiment detection, adaptive personality modes
 - Ebbinghaus decay, sister detection, quarantine system