{"id":"82ee5b62-ce53-4ddf-8716-5bb1dc104512","kind":"companies","code":"UB-C12561","name":"openclacky","nameBasis":"source-english","summary":"Most token-efficient open-source AI Agent","description":"OpenClacky is the most token-efficient open-source AI Agent. Capability on par with Claude Code, cost only 1/4 of Hermes, 50% less than OpenClaw. 100% open-source MIT, BYOK choose your model, extreme Harness engineering polished by two years of Agentic R&D.","country":null,"category":null,"originalName":"openclacky","eventDate":null,"website":"https://openclacky.com/","sourceUpdatedAt":"2026-10-26T00:00:00.000Z","englishUpdatedAt":"2026-11-01T02:25:28.922Z","reviewedAt":"2026-11-01T02:25:28.922Z","snapshotAt":"2026-11-01T00:40:31.077Z","sourceHash":"8726fb1446e744624f35538d30d22f1491dae7415411d4cb8696d5678056f793","companyId":null,"foundedYear":null,"logoUrl":null,"originalText":"最省 Token 的开源 AI Agent\n\nOpenClacky 是最省 Token 的开源 AI Agent。能力与 Claude Code 同档，成本仅 Hermes 的 1/4、比 OpenClaw 省 50%。100% 开源 MIT、BYOK 自选模型、两年 Agentic R&D 打磨的极致 Harness 工程。","sources":[],"related":[{"id":"baae085a-bb23-4a56-9a03-846e9a3ad7b9","kind":"products","code":"UB-D7503","name":"openclacky","nameBasis":"original-brand","summary":"OpenClacky is the most Token-efficient open-source AI Agent. Built for developers, creators, and teams who use AI Agents heavily, it tackles a practical problem: Agents can get work done, but long and multi-turn tasks burn money. OpenClacky's core value is not \"yet another AI assistant\"—it uses an engineered architecture to cut Agent usage cost while keeping near Claude Code-level task execution. It ships as open-source, local-run, BYOK: bring your own API Key and connect Claude, GPT, DeepSeek, Kimi, Gemini, Minimax, OpenRouter, and other OpenAI-compatible APIs without locking to one model or platform. Use a strong model for complex work and cheaper models for ordinary sub-tasks—you decide quality vs cost. In engineering, OpenClacky specializes around Prompt Cache: freezing the system prompt, dual cache markers, Insert-then-Compress, compress-on-idle, stable tool Schema, and related mechanisms raise cache reuse in long sessions and cut repeated input Token spend.","description":"OpenClacky is the most Token-efficient open-source AI Agent. Built for developers, creators, and teams who use AI Agents heavily, it tackles a practical problem: Agents can get work done, but long and multi-turn tasks burn money. OpenClacky's core value is not \"yet another AI assistant\"—it uses an engineered architecture to cut Agent usage cost while keeping near Claude Code-level task execution. It ships as open-source, local-run, BYOK: bring your own API Key and connect Claude, GPT, DeepSeek, Kimi, Gemini, Minimax, OpenRouter, and other OpenAI-compatible APIs without locking to one model or platform. Use a strong model for complex work and cheaper models for ordinary sub-tasks—you decide quality vs cost. In engineering, OpenClacky specializes around Prompt Cache: freezing the system prompt, dual cache markers, Insert-then-Compress, compress-on-idle, stable tool Schema, and related mechanisms raise cache reuse in long sessions and cut repeated input Token spend.","country":null,"category":"Coding assistants","originalName":"openclacky","eventDate":null,"website":null,"sourceUpdatedAt":"2026-10-28T16:00:18.534Z","englishUpdatedAt":"2026-10-29T00:52:59.449Z","reviewedAt":"2026-10-29T00:52:59.449Z","snapshotAt":"2026-10-29T00:45:28.937Z","sourceHash":"2a2455fa96ff3b089ee103dd8cf79051628a023f013b99e9a3b4e2d52198d916","companyId":"82ee5b62-ce53-4ddf-8716-5bb1dc104512","foundedYear":null,"logoUrl":null,"path":"/products/openclacky"}],"finance":{"funding":{"metric":"funding","count":0,"latest":null,"years":[],"points":[],"linePoints":[],"conflictGroups":0,"omittedRecordCount":0,"records":[],"totalRaised":null},"valuation":{"metric":"valuation","count":0,"latest":null,"years":[],"points":[],"linePoints":[],"conflictGroups":0,"omittedRecordCount":0,"records":[]},"revenue":{"metric":"revenue","count":0,"latest":null,"years":[],"points":[],"linePoints":[],"conflictGroups":0,"omittedRecordCount":0,"records":[]}},"events":[],"team":[],"productsRelated":[{"id":"baae085a-bb23-4a56-9a03-846e9a3ad7b9","kind":"products","code":"UB-D7503","name":"openclacky","nameBasis":"original-brand","summary":"OpenClacky is the most Token-efficient open-source AI Agent. Built for developers, creators, and teams who use AI Agents heavily, it tackles a practical problem: Agents can get work done, but long and multi-turn tasks burn money. OpenClacky's core value is not \"yet another AI assistant\"—it uses an engineered architecture to cut Agent usage cost while keeping near Claude Code-level task execution. It ships as open-source, local-run, BYOK: bring your own API Key and connect Claude, GPT, DeepSeek, Kimi, Gemini, Minimax, OpenRouter, and other OpenAI-compatible APIs without locking to one model or platform. Use a strong model for complex work and cheaper models for ordinary sub-tasks—you decide quality vs cost. In engineering, OpenClacky specializes around Prompt Cache: freezing the system prompt, dual cache markers, Insert-then-Compress, compress-on-idle, stable tool Schema, and related mechanisms raise cache reuse in long sessions and cut repeated input Token spend.","description":"OpenClacky is the most Token-efficient open-source AI Agent. Built for developers, creators, and teams who use AI Agents heavily, it tackles a practical problem: Agents can get work done, but long and multi-turn tasks burn money. OpenClacky's core value is not \"yet another AI assistant\"—it uses an engineered architecture to cut Agent usage cost while keeping near Claude Code-level task execution. It ships as open-source, local-run, BYOK: bring your own API Key and connect Claude, GPT, DeepSeek, Kimi, Gemini, Minimax, OpenRouter, and other OpenAI-compatible APIs without locking to one model or platform. Use a strong model for complex work and cheaper models for ordinary sub-tasks—you decide quality vs cost. In engineering, OpenClacky specializes around Prompt Cache: freezing the system prompt, dual cache markers, Insert-then-Compress, compress-on-idle, stable tool Schema, and related mechanisms raise cache reuse in long sessions and cut repeated input Token spend.","country":null,"category":"Coding assistants","originalName":"openclacky","eventDate":null,"website":null,"sourceUpdatedAt":"2026-10-28T16:00:18.534Z","englishUpdatedAt":"2026-10-29T00:52:59.449Z","reviewedAt":"2026-10-29T00:52:59.449Z","snapshotAt":"2026-10-29T00:45:28.937Z","sourceHash":"2a2455fa96ff3b089ee103dd8cf79051628a023f013b99e9a3b4e2d52198d916","companyId":"82ee5b62-ce53-4ddf-8716-5bb1dc104512","foundedYear":null,"logoUrl":null,"path":"/products/openclacky"}],"investors":[],"path":"/companies/openclacky","structured":{"city":null,"country":null,"location":null,"role":null,"category":null,"company":null},"definition":"openclacky is a company.","summaryBasis":"translated","thin":false,"canonical":"https://uniquebase.ai/companies/openclacky"}