SkillAgentSearch skills...

TrenchClaw

The high quality agentic ai Solana harness ✨ like openclaw 🦞 but specialized for Solana 👽 make trading bots, launch bots, build strategies, trade prediction markets and do research. Made with bun, solana/kit 6, Svelte, Helius, and more. Very gud tek 🤌🏼

Install / Use

/learn @henryoman/TrenchClaw
About this skill

Quality Score

0/100

Supported Platforms

Zed

README

<p align="center"> <img src="./public/banner.png" alt="TrenchClaw" width="640" /> </p> <p align="center"> <a href="https://github.com/henryoman/trenchclaw/releases/latest"><img src="https://img.shields.io/github/v/release/henryoman/trenchclaw?sort=semver&display_name=tag&style=for-the-badge&label=Release" alt="Latest release" /></a> <a href="https://bun.sh"><img src="https://img.shields.io/badge/Bun-1.3.11-000000?style=for-the-badge&logo=bun&logoColor=white" alt="Bun 1.3.11" /></a> <a href="https://ai-sdk.dev/"><img src="https://img.shields.io/npm/v/ai?style=for-the-badge&label=AI%20SDK&color=111827" alt="AI SDK version" /></a> <a href="https://x.com/mert"><img src="https://img.shields.io/badge/Teachings%20of%20Mert-000000?style=for-the-badge&logo=x&logoColor=white" alt="Teachings of Mert" /></a> <a href="https://phantom.app/"><img src="https://img.shields.io/badge/Phantom-AB9FF2?style=for-the-badge&logo=phantom&logoColor=white" alt="Phantom" /></a> <a href="https://anza.xyz/"><img src="https://img.shields.io/badge/Anza-1F5F3A?style=for-the-badge&logoColor=F5F5DC&labelColor=1F5F3A&color=1F5F3A" alt="Anza" /></a> <a href="https://github.com/anza-xyz/kit"><img src="https://img.shields.io/badge/Solana%20Kit-6.5.0-551BF9?style=for-the-badge&logo=solana&logoColor=white" alt="Solana Kit 6.5.0" /></a> <a href="https://www.metaplex.com"><img src="https://img.shields.io/badge/Metaplex-000000?style=for-the-badge&logo=metaplex&logoColor=white" alt="Metaplex" /></a> <a href="https://www.jup.ag"><img src="https://img.shields.io/badge/Jupiter-009A86?style=for-the-badge&logo=jupiter&logoColor=white" alt="Jupiter" /></a> <a href="https://www.helius.dev"><img src="https://img.shields.io/badge/Helius-000000?style=for-the-badge&logo=https%3A%2F%2Fwww.helius.dev%2Flogo.svg&logoColor=white" alt="Helius" /></a> <a href="https://solana.com"><img src="https://img.shields.io/badge/Solana-9945FF?style=for-the-badge&logo=solana&logoColor=white" alt="Solana" /></a> <a href="https://streamdown.ai/"><img src="https://img.shields.io/badge/Streamdown-0F172A?style=for-the-badge" alt="Streamdown" /></a> <a href="https://www.meteora.ag/"><img src="https://img.shields.io/badge/Meteora-FC030F?style=for-the-badge" alt="Meteora" /></a> <a href="https://ai-sdk.dev/tools-registry/bash-tool"><img src="https://img.shields.io/badge/Bash%20Tool-111827?style=for-the-badge&logo=gnu-bash&logoColor=white" alt="Bash Tool" /></a> <a href="https://www.browserbase.com/"><img src="https://img.shields.io/npm/v/%40browserbasehq%2Fstagehand?style=for-the-badge&label=Browserbase&color=000000" alt="Browserbase Stagehand version" /></a> <a href="https://vite.dev/"><img src="https://img.shields.io/npm/v/vite?style=for-the-badge&label=Vite%2B&color=646CFF" alt="Vite version" /></a> <a href="https://jsonrender.com/"><img src="https://img.shields.io/npm/v/%40json-render%2Fcore?style=for-the-badge&label=JSON%20Render&color=0EA5E9" alt="JSON Render version" /></a> <a href="https://www.npmjs.com/package/@googleworkspace/cli"><img src="https://img.shields.io/npm/v/%40googleworkspace%2Fcli?style=for-the-badge&label=Google%20Workspace%20CLI&color=34A853" alt="Google Workspace CLI version" /></a> <a href="https://svelte.dev/"><img src="https://img.shields.io/badge/Svelte-FF3E00?style=for-the-badge&logo=svelte&logoColor=white" alt="Svelte" /></a> <a href="https://bun.sh/docs/api/sqlite"><img src="https://img.shields.io/badge/SQLite-003B57?style=for-the-badge&logo=sqlite&logoColor=white" alt="SQLite" /></a> </p>

gud tek built by a long-time solami dev

Please give us a star if you're interested in seeing this project get fully built out. It will help me gauge interest. Thank you.

TrenchClaw

TrenchClaw is an openclaw-like agentic ai harness and runtime for the Solana blockchain. It's a personal solana assistant that executes modular on-chain actions, runs automated trading routines, and gives operators full visibility and control from our lightweight svelte gui. This is very dangerous and will be a while before security is perfected.

Built on @solana/kit and Bun from the ground up, with GUI/mobile surfaces planned for 1.0. Zero legacy dependencies (including legacy @solana/web3.js v1). Functional, composable, tree-shakeable. Designed for operators who care about what ships in their binary.

Current test requirement keys: helius api key for helius-backed reads, jupiter ultra key for swap flows, and an OpenRouter or Gateway API key for chat-driven workflows.

Full architecture: ARCHITECTURE.md

Translations

v0.1.0 Release Checklist

  • [x] AI chat with OpenRouter and Vercel AI Gateway
  • [x] Local instance sign-in, vault, and trading settings
  • [x] Managed wallet reads for balances and holdings
  • [x] Wallet creation, grouping, and renaming
  • [x] Helius RPC-based data fetching
  • [x] Dexscreener market and token research
  • [x] Jupiter Ultra swaps
  • [x] Jupiter Trigger API flows
  • [x] Queue jobs, scheduled Ultra swaps, and action sequences
  • [x] Direct transfers and token account cleanup
  • [x] Runtime memory, queue, and conversation history
  • [x] Operator chat now prefers token metadata and tickers over mint-only coin answers
  • [x] Desktop GUI for chat, wallets, keys, settings, activity, and runtime status
  • [ ] Full runtime settings editor in the GUI
  • [ ] Agent-managed scheduler
  • [ ] Standard swap paths beyond Jupiter Ultra
  • [ ] Telegram chat connector
  • [ ] Gatekeeper option for the Helius RPC link

Quick links:

Interested in sponsoring development? Support us: 7McYcR43aYiDttnY5vDw3SR6DpUxHG8GvLzhUsYFJSyA

Experimental software warning: this is currently unsafe, and unexpected behavior is highly likely if you use it.


Get Started

Use the docs for install and first-run:

Developer Runtime State

Local development should use the same per-instance runtime shape as the shipped product, while keeping mutable state outside the repo.

Default local dev behavior:

  • bun run dev uses ~/.trenchclaw-dev-runtime for runtime state
  • generated prompt-support files live under ~/.trenchclaw-dev-runtime/instances/<id>/cache/generated/
  • that state persists across reconnects and restarts
  • that state is personal/local and never part of the repo

Important rules for contributors, reviewers, and agents:

  • do not store personal vaults, wallets, logs, databases, or generated runtime state in this repository
  • .runtime/ is the tracked contract only; runtime code must never write there
  • the external dev runtime keeps local testing close to a real user install without polluting PRs
  • tests should use temporary runtime roots, not a shared developer runtime

Common setup:

# initialize the default external dev runtime once
bun run dev:runtime:init

# start local dev against the persistent external runtime
bun run dev

# copy selected instance state into the external dev runtime
bun run dev:instance:clone -- \
  --from-root /path/to/source-runtime \
  --to-root ~/.trenchclaw-dev-runtime \
  --from-instance 00 \
  --to-instance 00 \
  --parts wallets,db,settings

Useful overrides:

  • bun run dev -- --runtime-root /path/to/runtime --generated-root /path/to/runtime/instances/00/cache/generated
  • TRENCHCLAW_RUNTIME_STATE_ROOT=/path/to/runtime

The external dev runtime writes a managed .gitignore so secrets, keypairs, databases, logs, caches, and other personal testing state stay out of git by default.

Dashboard UI

<p align="center"> <img src="./public/v0-ui.png" alt="TrenchClaw main dashboard UI" width="1100" /> </p> <p align="center"> <em>Desktop chat, activity feed, wallet controls, settings, and live runtime console in one operator surface.</em> </p>

Runtime Architecture and Boundaries

TrenchClaw is a constrained execution runtime, not a free-form chatbot shell.

The shortest correct model is:

1) Runtime authority

  • apps/trenchclaw is the source of truth.
  • apps/frontends/gui is a client of the runtime.
  • apps/runner packages and launches the runtime plus GUI.

2) Tool system

  • Runtime tool definitions live under apps/trenchclaw/src/tools.
  • src/tools/registry.ts declares the runtime action tools and workspace tools.
  • src/tools/snapshot.ts builds the current tool snapshot from settings, filesystem policy, and release readiness.
  • src/ai/gateway/lanePolicy.ts chooses the tool subset for each lane.
  • src/runtime/chat/service.ts registers only that selected tool subset with the model.

3) Execution boundaries

  • Tools are typed and schema-validated before execution.
  • Settings-aware policy checks can block or require confirmation before dangerous actions run.
  • Filesystem access is constrained by runtime manifests and instance-scoped roots.
  • Workspace escape hatches like workspaceListDirectory, workspaceReadFile, and workspaceBash stay available only when policy allows them.

4) State model

  • .runtime is the repo-tracked contract and template area.
  • .runtime-state is the live mutable state root.
  • Each active instance owns its own settings, vault, wallets, logs, queue state, and workspace.

5) Why this matters

This design keeps the model on a narrow, explicit tool surface while still allowing enough freedom to inspect the runtime workspace and use a constrained shell when needed. The goal is a local operator runtime with auditable state transitions and deliberate

View on GitHub
GitHub Stars12
CategoryProduct
Updated5d ago
Forks0

Languages

TypeScript

Security Score

80/100

Audited on Apr 3, 2026

No findings