https://github.com/2389-research/speed-run
Token-efficient code generation pipeline - parallel implementation with hosted LLM (Cerebras) for ~60% token savings. Includes MCP server.
https://github.com/2389-research/speed-run
ai-agents anthropic automation cerebras claude claude-code claude-code-skills codegen hosted-llm llm mcp parallel race speed-run token-efficient turbo
Last synced: 7 days ago
JSON representation
Token-efficient code generation pipeline - parallel implementation with hosted LLM (Cerebras) for ~60% token savings. Includes MCP server.
- Host: GitHub
- URL: https://github.com/2389-research/speed-run
- Owner: 2389-research
- License: mit
- Created: 2026-04-02T22:41:01.000Z (26 days ago)
- Default Branch: main
- Last Pushed: 2026-04-20T18:40:09.000Z (8 days ago)
- Last Synced: 2026-04-20T18:42:10.453Z (8 days ago)
- Topics: ai-agents, anthropic, automation, cerebras, claude, claude-code, claude-code-skills, codegen, hosted-llm, llm, mcp, parallel, race, speed-run, token-efficient, turbo
- Language: JavaScript
- Homepage: https://2389-research.github.io/claude-plugins
- Size: 205 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- License: LICENSE