# linuxhsj/openclaw-zero-token

OpenClaw: Use All Major AI Models NO API Token! Claude/ChatGPT/Gemini/DeepSeek/Doubao/Grok/Qwen/Manus/Kimi

Repository: https://github.com/linuxhsj/openclaw-zero-token
Canonical: https://ross.abutalabs.com/products/openclaw-zero-token
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-08-17T04:00:28+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 78, longevity 13
- inputs: {"age_days": 191, "days_push": 16, "days_rel": 151, "gap_med": 6, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5154, forks 1230 (observed 2026-08-28T04:09:11.428789+00:00)

## What it is
OpenClaw Zero Token is a fork of OpenClaw that provides a unified gateway to major LLM providers (ChatGPT, Claude, Gemini, DeepSeek, Qwen, Doubao, Kimi, Grok, GLM, and more) without paid API keys, by driving the providers' official web UIs through browser login sessions. It exposes these web-backed models through a single local API so tools and agents can call them as if they were standard LLM endpoints.

## Use cases
- use chatgpt and claude from my code without paying for api keys
- unified gateway for multiple llm providers
- call gemini and deepseek through one openai-compatible endpoint
- run ai agents with free llm backends
- route prompts to different ai models without managing tokens
- self-host an llm proxy using my browser logins
- access kimi and qwen models programmatically for free

## When to choose
- you want to experiment with many LLM providers without API billing or credit cards
- you already have web accounts for these providers and want programmatic access through one gateway
- you're building personal tools or agents where occasional instability from web-driven access is acceptable
- you want credentials stored locally rather than API keys in code

## When to avoid
- production or commercial workloads — driving official web UIs typically violates provider terms of service and can get accounts banned
- you need guaranteed latency, throughput, or SLAs, since browser automation is fragile and rate-limited by the web UIs
- enterprise deployments with compliance requirements around sanctioned API usage
- you need models or providers not supported by the gateway

## Facets
- artifact type: service
- maturity: active
- function: llm-inference, proxy, api-framework, chatbot, agent-framework
- domain: large-language-models, artificial-intelligence, self-hosted, developer-tools
- platform: self-hosted, cross-platform, cli
- tags: llm-gateway, browser-automation, no-api-key, unified-api, openai-compatible, web-session-bridge, free-llm-access, ai-agents, nodejs, typescript

## Member repositories
- linuxhsj/openclaw-zero-token (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:11.428789+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:01:55.663316+00:00, confidence not recorded.
  - readme: https://github.com/linuxhsj/openclaw-zero-token (fetched 2026-08-28T04:09:11.428789+00:00, sha a8e3dd83d2f4)
- Data as of 2026-08-30T08:39:29.467469+00:00.