← Back to Skills Marketplace
jonathangu

CrabPath

by Jonathan Louis Gu · GitHub ↗ · v11.2.1
cross-platform ⚠ suspicious
523
Downloads
0
Stars
0
Active Installs
12
Versions
Install in OpenClaw
/install crabpath
Description
Memory graph engine with caller-provided embed and LLM callbacks; core is pure, with real-time correction flow and optional OpenAI integration.
README (SKILL.md)

CrabPath

Pure graph core: zero required deps and no network calls. Caller provides callbacks.

Design Tenets

  • No network calls in core
  • No secret discovery (no dotfiles, keychain, or env probing)
  • No subprocess provider wrappers
  • Embedder identity in state metadata; dimension mismatches are errors
  • One canonical state format (state.json)

Quick Start

from crabpath import split_workspace, HashEmbedder, VectorIndex

graph, texts = split_workspace("./workspace")
embedder = HashEmbedder()
index = VectorIndex()
for nid, content in texts.items():
    index.upsert(nid, embedder.embed(content))

Embeddings and LLM callbacks

  • Default: HashEmbedder (hash-v1, 1024-dim)
  • Real: callback embed_fn / embed_batch_fn (e.g., text-embedding-3-small)
  • LLM routing: callback llm_fn using gpt-5-mini (example)

Session Replay

replay_queries(graph, queries) can warm-start from historical turns.

CLI

--state is preferred:

crabpath query TEXT --state S [--top N] [--json] crabpath query TEXT --state S --chat-id CID

crabpath doctor --state S crabpath info --state S crabpath init --workspace W --output O --embedder openai crabpath query TEXT --state S --llm openai crabpath inject --state S --type TEACHING [--type DIRECTIVE]

Real-time correction flow: python3 query_brain.py --chat-id CHAT_ID python3 learn_correction.py --chat-id CHAT_ID

Quick Reference

  • crabpath init/query/learn/inject/health/doctor/info
  • query_brain.py --chat-id and learn_correction.py for real-time correction pipelines
  • query_brain.py traversal limits: beam_width=8, max_hops=30, fire_threshold=0.01
  • Hard traversal caps: max_fired_nodes and max_context_chars (defaults None; query_brain.py defaults max_context_chars=20000)
  • examples/correction_flow/, examples/cold_start/, examples/openai_embedder/

API Reference

  • Core lifecycle:
    • split_workspace
    • load_state
    • save_state
    • ManagedState
    • VectorIndex
  • Traversal and learning:
    • traverse
    • TraversalConfig
    • TraversalConfig.beam_width, .max_hops, .fire_threshold, .max_fired_nodes, .max_context_chars, .reflex_threshold, .habitual_range, .inhibitory_threshold
    • TraversalResult
    • apply_outcome
  • Runtime injection APIs:
    • inject_node
    • inject_correction
    • inject_batch
  • Maintenance helpers:
    • suggest_connections, apply_connections
    • suggest_merges, apply_merge
    • measure_health, autotune, replay_queries
  • Embedding utilities:
    • HashEmbedder
    • OpenAIEmbedder
    • default_embed
    • default_embed_batch
    • openai_llm_fn
  • LLM routing callbacks:
    • chat_completion
  • Graph primitives:
    • Node
    • Edge
    • Graph
    • split_workspace
    • generate_summaries

CLI Commands

  • crabpath init --workspace W --output O [--sessions S] [--embedder openai]
  • crabpath query TEXT --state S [--top N] [--json] [--chat-id CHAT_ID]
  • crabpath learn --state S --outcome N --fired-ids a,b,c [--json]
  • crabpath inject --state S --id NODE_ID --content TEXT [--type CORRECTION|TEACHING|DIRECTIVE] [--json] [--connect-min-sim 0.0]
  • crabpath inject --state S --id NODE_ID --content TEXT --type TEACHING
  • crabpath inject --state S --id NODE_ID --content TEXT --type DIRECTIVE
  • crabpath health --state S
  • crabpath doctor --state S
  • crabpath info --state S
  • crabpath replay --state S --sessions S
  • crabpath merge --state S [--llm openai]
  • crabpath connect --state S [--llm openai]
  • crabpath journal [--stats]
  • query_brain.py --chat-id CHAT_ID
  • learn_correction.py --chat-id CHAT_ID

Traversal defaults

  • beam_width=8
  • max_hops=30
  • fire_threshold=0.01
  • reflex_threshold=0.6
  • habitual_range=0.2-0.6
  • inhibitory_threshold=-0.01
  • max_fired_nodes (hard node-count cap, default None)
  • max_context_chars (hard context cap, default None; query_brain.py default is 20000)

Paper

https://jonathangu.com/crabpath/

Usage Guidance
This skill is internally coherent: the core is local and dependency-free, while OpenAI usage is optional and present only in helper modules and example/benchmark scripts. Before installing or running anything: 1) if you do not want any network activity, avoid running the examples/benchmarks or passing the --embedder/--llm flags that enable OpenAI; 2) if you enable OpenAI, only provide an API key to the runtime you control and inspect openai_* example code to ensure it uses the key only where you expect; 3) the daemon runs a JSON-RPC over stdin/stdout — treat it like any long-lived process that will load a state.json from a filesystem path you choose; 4) if you plan to run benchmarks or the daemon in production, run tests locally in an isolated environment and review state/save paths to avoid storing sensitive data in shared locations.
Capability Analysis
Type: OpenClaw Skill Name: crabpath Version: 11.2.1 The OpenClaw AgentSkills skill bundle, CrabPath, is classified as suspicious due to significant prompt injection vulnerabilities and a high-risk operational profile. The `examples/openclaw_adapter/agents_hook.md` file explicitly instructs an AI agent to execute `query_brain.py`, `learn_correction.py`, and `crabpath inject` commands with user-controlled input, creating direct prompt injection vectors against the agent's memory and decision-making. Additionally, the skill bundle exhibits extensive file system access (reading/writing state, logs, and workspace files), network communication (to OpenAI for embeddings and LLM routing), and frequent subprocess execution of its own CLI and Python scripts, including a persistent daemon. While these capabilities are integral to its stated purpose as a memory graph engine, their combination with direct user-input execution paths presents a notable security risk.
Capability Assessment
✓ Purpose & Capability
Name/description (memory graph with optional LLM/embed callbacks) matches the repository contents: core graph code, CLI, daemon, example adapters, and optional OpenAI helper files. The repo separates core (zero-deps hash embedder, VectorIndex, traversal) from optional OpenAI integration (openai_embeddings.py, openai_llm.py and benchmark/example scripts). No required env vars or binaries are declared, which aligns with the 'zero required deps' claim.
ℹ Instruction Scope
SKILL.md and README explicitly state core makes no network calls and that callers supply embed/LLM callbacks. The examples and benchmark scripts do perform network calls when run with the OpenAI client (they require an OpenAI client / API key if you choose that path). This is documented and opt-in; however, many example and benchmark files will perform network calls if executed, so users should be conscious about running those scripts.
✓ Install Mechanism
No install spec is included in the skill metadata (instruction-only skill). The repository contains source files but there is no remote download/install URL or package-fetching step in the skill metadata. That is low-risk from an install mechanism perspective.
ℹ Credentials
The skill declares no required environment variables or credentials (primaryEnv none). OpenAI integration and some benchmarks expect an OpenAI client / OPENAI_API_KEY if you choose to run them, but that is optional and appears to be clearly documented in README/benchmarks. No evidence of implicit secret discovery (dotfile/keychain probing) is present in the SKILL.md; the codebase follows an explicit opt-in pattern for API usage in examples/benchmarks.
✓ Persistence & Privilege
always:false and disable-model-invocation:false (normal). The package provides a daemon mode that keeps state in memory and exposes a JSON-RPC (NDJSON) protocol over stdin/stdout; this is a documented runtime mode and not secretly forced on agents. The daemon's behavior and state paths are explicit in docs (e.g., ~/.crabpath/main/state.json).
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install crabpath
  3. After installation, invoke the skill by name or use /crabpath
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v11.2.1
v11.2.1
v11.2.0
test
v11.1.0
v11.1.0
v9.1.0
Benchmarks fixture + adversarial tests + replay interactions
v8.0.0
Unified state, embedder validation, examples, design tenets, benchmarks
v6.1.0
Full sweep: deduplicated code, expanded exports, clean docs
v6.0.1
Pure callbacks. Zero deps. REPRODUCE.md for paper claims.
v5.0.1
Pure engine. All provider code removed. Callbacks only.
v2.0.0
Clean repo, rewritten README, repositioned for users. No API changes.
v1.0.9
Clarify interfaces, explain learning signal, auto-suggest session replay.
v1.0.0
Initial release. Memory graph for AI agents.
v1.0.8
Memory graph for AI agents.
Metadata
Slug crabpath
Version 11.2.1
License —
All-time Installs 0
Active Installs 0
Total Versions 12
Frequently Asked Questions

What is CrabPath?

Memory graph engine with caller-provided embed and LLM callbacks; core is pure, with real-time correction flow and optional OpenAI integration. It is an AI Agent Skill for Claude Code / OpenClaw, with 523 downloads so far.

How do I install CrabPath?

Run "/install crabpath" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is CrabPath free?

Yes, CrabPath is completely free (open-source). You can download, install and use it at no cost.

Which platforms does CrabPath support?

CrabPath is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created CrabPath?

It is built and maintained by Jonathan Louis Gu (@jonathangu); the current version is v11.2.1.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191113 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments