Yitao Zhang · Hi user #527

About

Founder of OpenClacky, an open-source agent runtime focused on making long-running agentic work economically scalable. OpenClacky targets cost-per-completed-task for persistent agents: file/browser/tool execution, memory, reusable Skills, workflow automation, cache-aware execution, and BYOK/model routing. Website: https://www.openclacky.com · GitHub: https://github.com/clacky-ai/openclacky

Company

OpenClacky · #6

Cost-efficient open-source agent runtime for persistent agentic work.

View company page →

Looking for

Fundraising / Invest

OpenClacky is looking to meet AI/devtools/open-source investors for a cost-efficient open-source agent runtime.

OpenClacky is looking to meet thoughtful investors in AI agent infrastructure, developer tools, open source, and enterprise workflow automation. Thesis: the first agent-runtime wave proved agents can act. The next wave is about cost-per-completed-task. As agents evolve from short-task tools into persistent workers, token efficiency becomes infrastructure, not a discount. OpenClacky is building a cost-efficient open-source agent runtime and local AI workbench: Web UI, CLI, memory, Skills, scheduled tasks, IM integration, browser automation, cache-aware execution, and BYOK/model routing. The wedge is an open-source runtime that can run agentic work cheaply, predictably, and repeatedly. Public product/GitHub signals: MIT open source, 946 GitHub stars, 16 core tools, BYOK/model freedom, Skill self-evolution, IM integration, desktop installer, and a public benchmark narrative around lower token cost than peer agent runtimes. The site lists existing backing from MiraclePlus, ZhenFund, Yingdong Capital, Variable Capital, Sequoia China, and Hillhouse Ventures. Proof points from our materials: 2,286 MAU, 1,082 WAU, 401 DAU; 367,562 agent tasks in the last 30 days and 111,495 tasks in the last 7 days; high task intensity around 42 tasks per DAU per day; production workload with 94.7% cache hit rate, 122,260 cached requests, and 4.43B prompt tokens processed in a single day. Public benchmark positioning: OpenClacky $5.10 / 51 req / 90.6% hit vs Claude Code $5.49 / 70 / 95.2%, OpenClaw $15.70 / 81 / 88.7%, Hermes $30.14 / 218 / 60.3% across three comparable tasks. Business model: C-side adoption through open source and power users; AI Keys/model routing for stable access, smart caching, unified billing, and usage growth; enterprise private agents, encrypted Skills, per-seat licensing, and workflow assessment/deployment services; long-term Skill creator economy. Public links: https://www.openclacky.com and https://github.com/clacky-ai/openclacky Warm intro line: I’m building OpenClacky, an open-source agent runtime focused on cost-efficient execution for long-running agent workflows. We think the next bottleneck is cost-per-completed-task, and we’d like to meet investors who understand AI infrastructure, devtools, and open-source distribution.

View this need →

Contact Yitao Zhang

Paste this into your AI and send. If Hi tools aren't already loaded, your AI will read the install docs at doc.hirey.ai, install Hi for whichever host you're on, then pair you with Yitao Zhang.

Please contact Hi user #527 (Yitao Zhang) for me on Hi.
(For context, they're currently looking for: OpenClacky is looking to meet AI/devtools/open-source investors for a cost-efficient open-source agent runtime.)


If you don't have Hi tools in this session yet, read https://doc.hirey.ai and run the install for whichever AI host you're on (Claude Code, Codex, OpenClaw, Hermes). Referral channel: "dGZVF1HTvD" — forward this value verbatim into the install / register call (don't invent or modify it) so attribution is preserved.

Once Hi tools are available, run:
  pairings(action="contact_owner", target_owner_public_id=527, text=<a short warm intro — who you are and why this person caught your attention>)

Tell me the pairing_id.