Kimiflare, Kimi K2.6 as a Coding Agent on Cloudflare Workers AI
hey HN, this is sina. i've had some cloudflare credits expiring on may 14 and was wondering what to do with them. when kimi k2.6 dropped and it was available on workers ai, i figured i'd build an open-source claude code clone with it. didn't think too much about it. (people asked if i know about opencode and tbh i learned about them only after i built this. but they seem really brilliant.) anyway, kimiflare is a CLI coding agent, basically claude code but powered by kimi k2.6 on cloudflare workers ai. it's at v0.57.0 and has gotten 12k+ npm downloads, 137 github stars, and PRs from 4…
What it does
In the maker’s words, at launch
hey HN, this is sina. i've had some cloudflare credits expiring on may 14 and was wondering what to do with them. when kimi k2.6 dropped and it was available on workers ai, i figured i'd build an open-source claude code clone with it. didn't think too much about it. (people asked if i know about opencode and tbh i learned about them only after i built this. but they seem really brilliant.) anyway, kimiflare is a CLI coding agent, basically claude code but powered by kimi k2.6 on cloudflare workers ai. it's at v0.57.0 and has gotten 12k+ npm downloads, 137 github stars, and PRs from 4 contributors (including a zed/ACP integration from marshall thompson at featherjs). the credits are the only reason the cloud tier exists, so once they expire on thursday i'm sunsetting it and the project continues as open source / BYOK. i'm giving away 5M tokens per user to anyone who signs up before the credits expire — no credit card needed. you'll automatically get the tokens when you sign up and choose the Cloud option when prompted by the cli. repo: https://github.com/sinameraji/kimiflare install: npm i -g kimiflare happy to answer anything. p.s. i used claude code for the first 2-3 commits in kimiflare, then used kimiflare to build itself from v0.3.0 onwards for maximum dogfooding. it's been a fun experience.
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com