OSS Radar
Back

ThinkWatch-Lite alternatives

ThinkWatchProject/ThinkWatch-Lite (630 stars, +137 this week): Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API… Why it matters: useful plumbing for shipping LLM-powered features.

Below are 12 other LLM tooling repos tracked by OSS Radar that share at least two GitHub topics with ThinkWatch-Lite, ordered by how many topics overlap, then by stars gained in the last 7 days. Topic overlap means a similar problem space, not a drop-in replacement, so check each project's README.

  1. 1. diegosouzapw/OmniRoute

    +2k/wkest.

    Never stop coding. Free MIT AI gateway: one endpoint, 359 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek… Why it matters: useful plumbing for shipping LLM-powered features.

    76k stars · TypeScript · shared topics: ai-gateway, anthropic, claude-code, codex, llm-gateway, openai

  2. 2. decolua/9router

    +294/wkest.

    Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Why it matters: useful plumbing for shipping LLM-powered features.

    31k stars · JavaScript · shared topics: ai-gateway, anthropic, claude-code, codex, llm-gateway, openai

  3. 3. lidge-jun/opencodex

    +259/wkest.

    Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK… Why it matters: useful plumbing for shipping LLM-powered features.

    17k stars · TypeScript · shared topics: ai-gateway, anthropic, claude-code, codex, llm-proxy, openai

  4. 4. NousResearch/hermes-agent

    +1.6k/wkest.

    The agent that grows with you. Why it matters: useful plumbing for shipping LLM-powered features.

    254k stars · Python · shared topics: anthropic, claude-code, codex, openai

  5. 5. BerriAI/litellm

    +462/wkest.

    The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails… Why it matters: useful plumbing for shipping LLM-powered features.

    61k stars · Python · shared topics: ai-gateway, anthropic, llm-gateway, openai

  6. 6. trailhq/Trail-Code

    +294/wkest.

    Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your… Why it matters: useful plumbing for shipping LLM-powered features.

    10k stars · TypeScript · shared topics: anthropic, claude-code, codex, openai

  7. 7. asgeirtj/system_prompts_leaks

    +273/wkest.

    Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Why it matters: useful plumbing for shipping LLM-powered features.

    70k stars · Python · shared topics: anthropic, claude-code, codex, openai

  8. 8. lokicorvus/crosspet

    +105/wkest.

    跨 AI 桌宠：跟着你用的 AI 换形象、跟着 AI 的工作状态做动作. Why it matters: useful plumbing for shipping LLM-powered features.

    161 stars · C# · shared topics: claude-code, codex, macos, windows

  9. 9. qunqin24/Pulse

    +91/wkest.

    Know how much Claude Code, Codex, Cursor, Copilot and 70+ other AI coding tools you have left — a free, open-source macOS monitor on the… Why it matters: useful plumbing for shipping LLM-powered features.

    551 stars · Swift · shared topics: claude-code, codex, macos, openai

  10. 10. yakuikai/tokentab

    +1.4k/wkest.

    Local-first CLI and web dashboard that reads Claude Code, Codex and Gemini CLI session logs and shows token usage and cost by model… Why it matters: useful plumbing for shipping LLM-powered features.

    780 stars · Python · shared topics: claude-code, codex, token-usage

  11. 11. headroomlabs-ai/headroom

    +630/wkest.

    Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. Why it matters: useful plumbing for shipping LLM-powered features.

    75k stars · Python · shared topics: anthropic, claude-code, openai

  12. 12. code-yeongyu/oh-my-openagent

    +126/wkest.

    OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering. Why it matters: useful plumbing for shipping LLM-powered features.

    70k stars · TypeScript · shared topics: anthropic, codex, openai

More: all trending LLM tooling repos · compare ThinkWatch-Lite with the top 2