chaos-mindHybrid search memory system for AI agents. Manual search and storage - auto-capture is opt-in only.
Install via ClawdBot CLI:
clawdbot install hargabyte/chaos-mindContext-aware Hierarchical Autonomous Observation System
Hybrid search memory for AI agents with 4 retrieval signals:
First time? Run this to see the complete reference:
chaos-cli --helpQuick workflow:
chaos-cli search "keywords" --mode index --limit 10chaos-cli store "important fact" --category decision --priority 0.9chaos-cli list 10Token savings: Use --mode index for 90% token savings (~75 tokens/result)
More help: Run chaos help-agents for the AI-optimized reference guide.
After installation, use chaos-cli:
# Search memories
chaos-cli search "pricing decisions" --limit 5
# Store a memory
chaos-cli store "Enterprise tier: $99/month" --category decision
# List recent
chaos-cli list 10Quick search (summary mode):
chaos-cli search "architecture patterns" --mode summary --limit 5Fast scan (index mode, 90% token savings):
chaos-cli search "team decisions" --mode index --limit 10Full detail:
chaos-cli search "model selection" --mode full --limit 3Modes:
| Mode | Tokens/Result | Use Case |
|------|---------------|----------|
| index | ~75 | Quick scan, many results |
| summary | ~250 | Balanced (default) |
| full | ~750 | Deep dive |
# Decision
chaos-cli store "Qwen3-1.7B is default model" --category decision --priority 0.9
# Core fact
chaos-cli store "Database runs on port 3307" --category core --priority 0.7
# Research finding
chaos-cli store "43x speedup with think=false" --category research --priority 0.8Categories: decision, core, semantic, research
Priority: 0.0-1.0 (higher = more important)
chaos-cli get <memory-id>chaos-cli list # Default 10
chaos-cli list 20 # Show 20ā ļø DISABLED BY DEFAULT for privacy.
To enable auto-capture:
nano ~/.chaos/config/consolidator.yamlauto_capture.enabled: trueauto_capture.sourcesollama pull qwen3:1.7bchaos-consolidator --auto-capture --onceWhat it extracts: Decisions, facts, insights
What it skips: Greetings, filler, acknowledgments
Where it runs: 100% local (your machine, no external APIs)
Speed: 2.6s per message (~42s per 16-message session)
Privacy: Only processes files you explicitly configure. See SECURITY.md for details.
CHAOS Memory integrates with other tools for deeper intelligence:
What it does: Anchors memories to specific code locations and files
Why use it: Memories become context-aware - "this decision affects Auth.tsx lines 45-67"
How it works:
cx is available at startupmemory ā code locationInstall Cortex:
# Cortex is a separate tool
# Install from: https://github.com/hargabyte/cortexExample:
# Without Cortex
chaos-cli search "auth flow"
ā "Changed auth to use JWT tokens"
# With Cortex
chaos-cli search "auth flow"
ā "Changed auth to use JWT tokens"
ā š Auth.tsx:45-67, middleware/auth.js:12What it does: Links memories to tasks and issues
Why use it: Track which memories led to which tasks, decisions to implementations
How it works:
beads or beads-rust is availablememory ā taskInstall Beads:
# Beads is a separate task management tool
# Install from: https://github.com/hargabyte/beadsExample:
# Store memory with task reference
chaos-cli store "Need to refactor auth" --category decision --task AUTH-123
# Search shows related tasks
chaos-cli search "auth refactor"
ā "Need to refactor auth"
ā š Task: AUTH-123 (In Progress)When all three tools work together:
chaos-cli search "performance optimization"
ā Memory: "Added Redis caching layer"
ā š Code: cache/redis.js:34-89
ā š Task: PERF-042 (Completed)
ā š Related: 3 other memories, 2 code files, 1 PRStatus Detection:
[OPT] Cortex Engine: FOUND)[OPT] Beads Task Manager: FOUND)chaos-mcpDefault config location: ~/.chaos/config/consolidator.yaml
# Auto-capture is DISABLED by default
auto_capture:
enabled: false # Change to true after configuring paths
sources: [] # Add your session paths here
# Example (uncomment after reviewing):
# sources:
# - ~/.openclaw-*/agents/*/sessions/*.jsonl
qwen:
model: qwen3:1.7b # Locked default
chaos:
mode: mcp
mcp:
env:
CHAOS_DB_PATH: "~/.chaos/db"| Variable | Default | Description |
|----------|---------|-------------|
| CHAOS_HOME | ~/.chaos | Installation directory |
| CHAOS_DB_PORT | 3307 | Database port |
| CHAOS_MODEL | qwen3:1.7b | Extraction model |
The install script handles dependencies automatically.
Command not found:
export PATH="$HOME/.chaos/bin:$PATH"Database error:
cd ~/.chaos/db && dolt sql-server --port 3307 &No results:
chaos-cli list # Check if memories existData Storage: All memories stored locally on your machine (~/.chaos/db)
Auto-Capture (Opt-In):
~/.chaos/config.yamlauto_capture.sourcesPermissions:
~/.chaos/db)Control:
# View what auto-capture will process (dry-run)
chaos-consolidator --auto-capture --once --dry-run
# Disable auto-capture
# Edit ~/.chaos/config.yaml:
# auto_capture:
# enabled: false
# Or simply don't configure session pathsTransparency:
install.sh)dolt sql)Version 1.0.0 | Created by HSA Team
Generated Mar 1, 2026
A development team uses CHAOS Memory to track architectural decisions and code changes across sprints. By storing decisions with Cortex integration, they link memories to specific code files, enabling new team members to quickly understand why certain implementations exist and reducing onboarding time.
Researchers employ CHAOS Memory to document findings and insights from experiments. Using the store command with categories like research, they capture key data points and hypotheses, while search with index mode allows for efficient retrieval of relevant past work during literature reviews or paper writing.
A support team utilizes CHAOS Memory to log common issues and resolutions. By storing memories with priority levels, they highlight critical solutions, and the hybrid search helps agents quickly find answers during live chats, improving response times and customer satisfaction.
Product managers use CHAOS Memory with Beads integration to link feature decisions to specific tasks or issues. This creates a traceable history of why features were prioritized or changed, aiding in stakeholder reporting and ensuring alignment across teams during product development cycles.
Legal professionals apply CHAOS Memory to organize case details, precedents, and client information. The vector search enables semantic retrieval of similar cases, while manual storage ensures sensitive data remains controlled, supporting efficient case preparation and strategy development.
Offer a free tier with basic memory storage and search features, while charging for advanced integrations like Cortex and Beads, auto-capture capabilities, and higher usage limits. This attracts individual developers and small teams, with upsell opportunities for enterprises needing enhanced tooling.
Sell annual licenses to large organizations for on-premise or private cloud deployment, including dedicated support, custom integrations, and enhanced security features. This model targets industries with strict data privacy requirements, such as healthcare or finance, ensuring compliance and scalability.
Provide consulting services to help clients integrate CHAOS Memory into their existing workflows, offering custom configurations, training sessions, and development of tailored plugins. This complements the core tool by addressing specific business needs and fostering long-term partnerships.
š¬ Integration Tip
Start by enabling auto-capture only after reviewing privacy settings, and integrate Cortex or Beads gradually to enhance memory context without overwhelming users.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection