Halo Harness — Development skill for Claude Code
Halo Harness: an intuitive, Claude Code-compatible agent harness that drives DeepSeek, GLM, Kimi, Qwen and Claude over Databricks, OpenRouter, the Anthropic API and your Claude Code subscription, reus.
How to install Halo Harness
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open roloVibes/Halo-Harness and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Halo Harness does
Halo Harness: an intuitive, Claude Code-compatible agent harness that drives DeepSeek, GLM, Kimi, Qwen and Claude over Databricks, OpenRouter, the Anthropic API and your Claude Code subscription, reusing your existing Claude Code configuration.
Alternatives in Development
- IPolloWork — Enterprise-grade, local-first Agent Workbench for people and agent teams 4.9k ★
- Petdex — A public gallery of animated pets for Codex, Claude Code, DeepSeek Harness, Hermes, OpenCode, Gemini CLI, and 4k ★
- Dario — A local OpenAI- and Anthropic-compatible proxy that brings your Claude Pro/Max subscription to Cursor, Cline 485 ★
README
Halo Harness
**A Claude Code-compatible agent harness that runs the models you choose.** Halo gives DeepSeek, GLM, Kimi, Qwen and Claude the same tools, the same configuration and the same working habits as Claude Code, over Databricks, OpenRouter, the Anthropic API or your Claude Code subscription, and it reads your existing Claude Code setup so nothing has to be configured twice.
Quick start (Kali / Linux)
Prerequisites: `git`, Python 3.10 or newer, and [`uv`](https://docs.astral.sh/uv/getting-started/installation/) (`curl -LsSf https://astral.sh/uv/install.sh | sh`, then open a new shell). One line clones, installs, verifies and runs `halo doctor`:
curl -fsSL https://raw.githubusercontent.com/roloVibes/Halo-Harness/master/scripts/install-halo.sh | bash
Or by hand:
git clone https://github.com/roloVibes/Halo-Harness.git
cd Halo-Harness
uv tool install --reinstall . # or: pipx install --force -e .
cd ~ # cd anywhere: halo is a real command on PATH now
halo init # pick a provider, paste one credential, get a live pong
halo # the full-screen TUI
No clone at all: `uv tool install git+https://github.com/roloVibes/Halo-Harness`. [docs/INSTALL.md](docs/INSTALL.md) is the one-page version of this section, including upgrades and the offline recipe for a locked-down work box.
Windows
Install `uv` first (`powershell -ExecutionPolicy ByPass -c "ir
Related Skills
Lite
A fast, local workspace for Claude Code, Codex, Gemini CLI, Kimi Code, Qwen Code, DeepSeek, OpenRouter, and yo
Linktokenview Docs
LinkTokenView(联视未来)国产大模型 Token API 聚合平台,提供 OpenAI 兼容接口,统一调用 DeepSeek v4.1、Kimi、GLM、通义千问 等模型,支持 Token Plan 与 Co
Claude Code Provider Switching Kit
Switch Claude Code between Anthropic, GLM, and OpenRouter (including free models) with one command.
Subscription Proxy Zcode
Agent Skill para conectar assinaturas pagas de IA (Gemini pool 4 contas, Claude, Codex) e modelos comunitarios
Wtagent
Turn ChatGPT Web (including Pro) into Codex. Turn Claude Web into Claude Code. Also DeepSeek, Gemini, Grok, Ki
Q Agent
Self-hosted llama.cpp stack for Qwen + MTP (multi-token prediction): a 125B MoE read from ≥ 80 GB of RAM, or a
Related Agents
ChatGPT On Wechat
CowAgent是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长,比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页
Glm
Hands a well-scoped coding task (implement, refactor, write tests, fix a bug) to GLM 5.3 Flash via OpenRouter
Openrouter Agent
Runs a model from any of ~60 vendors through OpenRouter's OpenAI-compatible endpoint, billed per token against