firm-hebbian-memory
Système de mémoire adaptative hebbienne pour Claude.md — transforme les logs de sessions en patterns pondérés qui renforcent ou atrophient les règles de…
Skill by romainsantoli-web
Chalk Labs
Need help deploying firm-hebbian-memory?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/romainsantoli-web-firm-hebbian-memory
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/firm-hebbian-memory
What's inside
- Skill name
firm-hebbian-memory- Description
- Système de mémoire adaptative hebbienne pour Claude.md — transforme les logs de sessions en patterns pondérés qui renforcent ou atrophient les règles de travail selon l'usage réel. Implémente le Cahier des Charges v1.0.0 "Système de Mémoire Adaptative Hebbienne + Base Vectorielle pour Claude.md".
- License
- MIT
- Instructions
- 217 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Files (1)
- SKILL.md
SKILL.md (first lines)
# firm-hebbian-memory
> ⚠️ Contenu généré par IA — validation humaine requise avant déploiement en production.
## Purpose
Ce skill rend le **Claude.md vivant et auto-évolutif** via des mécanismes inspirés
de la plasticité synaptique hebbienne. Les patterns de travail qui se répètent sont
renforcés, ceux qui deviennent obsolètes s'atrophient naturellement.
**Inspiration neurobiologique :**
- **Plasticité hebbienne** → renforcement des poids Layer 2 par co-activation
- **Mémoire hippocampique** → stockage épisodique en base vectorielle (pgvector)
- **Consolidation néocorticale** → job d'analyse transformant les épisodes en schémas
## Architecture — 4 couches Claude.md (CDC §3.3)
| Couche | Nom | Modification |
|--------|-----|-------------|
| Layer 1 | CORE (immuable) | Humain uniquement |
| Layer 2 | CONSOLIDATED PATTERNS | Auto-mise à jour (poids hebbiens) |
| Layer 3 | EPISODIC INDEX | Auto-mise à jour (pointeurs sessions) |
| Layer 4 | META INSTRUCTIONS | Lecture seule pour le système auto |
## Tools activés (8 tools)
### Runtime (2 tools)
```
openclaw_hebbian_harvest — ingest JSONL session logs → SQLite (PII stripped)
openclaw_hebbian_weight_update — calcul/application des poids hebbiens (dry_run par défaut)
```
### Audit (6 tools)
```
openclaw_hebbian_analyze — analyse co-activation patterns (Jaccard)
openclaw_hebbian_status — dashboard poids, atrophie, promotions
openclaw_hebbian_layer_validate — validation structure 4 couches
openclaw_hebbian_pii_check — audit config PII stripping
openclaw_hebbian_decay_config_check — validation paramètres hebbiens
openclaw_hebbian_drift_check — détection drift sémantique vs baseline
```
## Formule de mise à jour des poids (CDC §4.3)
```python
nouveau_poids = ancien_poids + (learning_rate × activation) - (decay × (1 - activation))
# Paramètres par défaut
learning_rate = 0.05 # Renforcement si activée
decay = 0.02 # Atrophie si non-activée
poids_min = 0.0 # Floor — suppression si < 0.10
poids_max = 0.95 # Ceiling — promotion CORE si > 0.95
```
## Seuils de consolidation
| Transition | Condition |
|-----------|-----------|
| Épisodique → Émergent | Activé 5 sessions consécutives |
| Émergent → Fort | poids > 0.8 sur 20 sessions |
| Fort → CORE | **Validation humaine obligatoire** |
| Atrophie → Suppression | poids < 0.10 pendant 4 semaines + PR humaine |
## Sécurité (CDC §5.2)
- **PII stripping obligatoire** : regex sur emails, phones, IPs, API keys, SSN, JWT, AWS keys, chemins Unix home
- **Secrets détectés** : session rejetée + alerte immédiate
- **Accès BDD** : localhost/VPN uniquement
- **Rotation embeddings** : policy de ré-embedding si fuite suspectée
- **Réversibilité** : chaque modification = 1 commit Git atomique
- **Path whitelist** : configurable via `HEBBIAN_ALLOWED_DIRS` (env) — protège containers/multi-user
### Limitations connues (PII)
Le stripping regex couvre les catégories les plus courantes (10 patterns) mais ne
détecte pas les credentials embarqués dans des URLs de connexion (e.g.
`postgres://user:password@host/db`) ni les variables d'environnement loguées dans
des stack traces (`DB_URL=...`). Un scanner de secrets dédié (e.g. `trufflehog`,
`detect-secrets`) est recommandé en complément pour les environnements à haute
sensibilité.
## Anti-dérive (CDC §5.1)
- Aucune règle ne peut atteindre poids = 1.0 automatiquement (max 0.95)
- Détecteur de drift : alerte si cosine similarity vs baseline < 0.7
- 3 changements auto consécutifs → review forcée
- Snapshot mensuel archivé en Git tag
## Pipeline global
```
[ Session Claude Code ]
↓ fin de session
[ openclaw_hebbian_harvest ] → extrait résumé + tags + règles (PII stripped)
↓
[ SQLite local ] → stockage épisodique structuré
↓
[ openclaw_hebbian_analyze ] → clustering Jaccard + co-activations
↓
[ openclaw_hebbian_weight_update ] → mise à jour Layer 2 (dry_run=True)
↓
[ Human Review ] → validation avant application (dry_run=False)
```
## Hook post-session (MVP)
Sans hook automatique, l'ingestion reste manuelle — adoption = zéro.
Voici le minimum pour boucler le pipeline dès le MVP.
### Option A — Script shell (le plus simple)
Créer `~/.openclaw/hooks/post-session.sh` :
```bash
#!/usr/bin/env bash
# Hook post-session: ingest le dernier JSONL automatiquement
set -euo pipefailFrom romainsantoli-web/setup-vs-agent-firm, MIT.
More from romainsantoli-web/setup-vs-agent-firm
- 0.409score
firm-delivery-export
romainsantoli-web
Post-processing skill for firm-orchestration: converts the structured JSON output of a multi-agent workflow run into real deliverables — GitHub Pull Requests…
SkillDFreshness: DClaude Code +9 - 0.409score
firm-a2a-bridge
romainsantoli-web
Agent-to-Agent (A2A) Protocol RC v1.0 bridge for OpenClaw agents.
SkillDFreshness: DClaude Code +9 - 0.406score
firm-advanced-security-pack
romainsantoli-web
Advanced security audit pack covering secrets lifecycle, path canonicalization, exec plan freeze, hook routing, config includes, prototype pollution, safeBins…
SkillDFreshness: DClaude Code +9 - 0.406score
firm-agent-orchestration-pack
romainsantoli-web
Multi-agent task orchestration pack.
SkillDFreshness: DClaude Code +9 - 0.406score
firm-auth-compliance-pack
romainsantoli-web
Authentication and compliance audit pack.
SkillDFreshness: DClaude Code +9 - 0.406score
firm-browser-audit-pack
romainsantoli-web
Browser automation security audit pack.
SkillDFreshness: DClaude Code +9 - 0.406score
firm-config-migration-pack
romainsantoli-web
Configuration migration and integrity audit pack.
SkillDFreshness: DClaude Code +9 - 0.406score
firm-ecommerce-pack
romainsantoli-web
Curated skill bundle for e-commerce platforms, D2C brands and marketplace operators.
SkillDFreshness: DClaude Code +9 - 0.406score
firm-ecosystem-audit-pack
romainsantoli-web
Ecosystem differentiation audit pack.
SkillDFreshness: DClaude Code +9 - 0.406score
firm-gateway-hardening-pack
romainsantoli-web
Gateway authentication hardening and credentials audit pack.
SkillDFreshness: DClaude Code +9 - 0.406score
firm-legal-pack
romainsantoli-web
Curated skill bundle for law firms, legal departments and compliance teams.
SkillDFreshness: DClaude Code +9 - 0.406score
firm-legal-status-pack
romainsantoli-web
Legal status analysis and corporate structuring pack.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Feb 28, 2026 (8 months ago)
- Last release
- Mar 3, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from romainsantoli-web
- 0.618score
Memory OS AI
romainsantoli-web
Adaptive memory for AI agents — FAISS search, chat extraction, cross-project linking
ConnectorAFreshness: ALocal★ 3↓ 124/wkClaude Code +5 - 0.426score
MCP OpenClaw Extensions
romainsantoli-web
138-tool MCP server for AI agent firms: security, A2A, Hebbian memory, fleet mgmt
ConnectorDFreshness: DLocal↓ 31/wkClaude Code +5 - 0.409score
firm-delivery-export
romainsantoli-web
Post-processing skill for firm-orchestration: converts the structured JSON output of a multi-agent workflow run into real deliverables — GitHub Pull Requests…
SkillDFreshness: DClaude Code +9 - 0.409score
firm-a2a-bridge
romainsantoli-web
Agent-to-Agent (A2A) Protocol RC v1.0 bridge for OpenClaw agents.
SkillDFreshness: DClaude Code +9 - 0.406score
firm-agent-orchestration-pack
romainsantoli-web
Multi-agent task orchestration pack.
SkillDFreshness: DClaude Code +9 - 0.406score
firm-advanced-security-pack
romainsantoli-web
Advanced security audit pack covering secrets lifecycle, path canonicalization, exec plan freeze, hook routing, config includes, prototype pollution, safeBins…
SkillDFreshness: DClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get firm-hebbian-memory running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
firm-hebbian-memory skill. Agent Mart. https://agentmart.dev/skills/romainsantoli-web-firm-hebbian-memory (last updated 2026-10-24)