FlashML-org/FreeTokenPublic

FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

AI summary: An edge-native MoE serving engine for running frontier-scale AI models on personal hardware.

Stars
17.4K
+191 today
Forks
1.7K
Watchers
106
Open issues
280
Open PRs
191
Contributors
~26
Commits
230
Branches
133
Views (30d)
2

PythonApache-2.0Created Jul 20, 2026Last push todayLatest release v0.2.2+291 stars this week+2.8K this month

Quick answers

What is FreeToken?
An edge-native MoE serving engine for running frontier-scale AI models on personal hardware.
What does FreeToken do?
FreeToken is a high-performance inference engine optimized for running massive Mixture-of-Experts models locally on consumer hardware. It treats heterogeneous edge resources like GPUs, CPUs, and system memory as a unified compute platform to handle models scaling up to 290 billion parameters. The engine utilizes advanced memory management, semantic caching, and bandwidth-adaptive co-execution to deliver blistering interactive speeds. It provides OpenAI-compatible APIs, allowing seamless integration with existing tools and frameworks.
Who is FreeToken for?
AI enthusiasts, researchers, and developers with consumer GPU hardware. It is designed for users wanting to run massive MoE models without enterprise server equipment.
How popular is FreeToken on GitHub?
FlashML-org/FreeToken has 17,444 stars and 1,733 forks on GitHub, and gained 291 stars in the last 7 days.
What license does FreeToken use?
FlashML-org/FreeToken is released under the Apache-2.0 license.

Star history

since Sep 21, 2026
05K10K15KSep 2026Oct 2026Oct 2026Nov 2026
17.4K stars as of Nov 21, 2026. Measured daily since Sep 21, 2026; GitHub no longer exposes earlier star timestamps.

Update history

2 recorded
  • Nov 13, 2026New release v0.2.2 (previously v0.2.1).
  • Oct 30, 2026New release v0.2.1 (previously v0.1.3).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-16: 0 commits2025-11-17: 0 commits2025-11-18: 0 commits2025-11-19: 0 commits2025-11-20: 0 commits2025-11-21: 0 commits2025-11-22: 0 commits2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 0 commits2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 0 commits2026-01-21: 0 commits2026-01-22: 0 commits2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 0 commits2026-02-04: 0 commits2026-02-05: 0 commits2026-02-06: 0 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 0 commits2026-02-17: 0 commits2026-02-18: 0 commits2026-02-19: 0 commits2026-02-20: 0 commits2026-02-21: 0 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 0 commits2026-02-25: 0 commits2026-02-26: 0 commits2026-02-27: 0 commits2026-02-28: 0 commits2026-03-01: 0 commits2026-03-02: 0 commits2026-03-03: 0 commits2026-03-04: 0 commits2026-03-05: 0 commits2026-03-06: 0 commits2026-03-07: 0 commits2026-03-08: 0 commits2026-03-09: 0 commits2026-03-10: 0 commits2026-03-11: 0 commits2026-03-12: 0 commits2026-03-13: 0 commits2026-03-14: 0 commits2026-03-15: 0 commits2026-03-16: 0 commits2026-03-17: 0 commits2026-03-18: 0 commits2026-03-19: 0 commits2026-03-20: 0 commits2026-03-21: 0 commits2026-03-22: 0 commits2026-03-23: 0 commits2026-03-24: 0 commits2026-03-25: 0 commits2026-03-26: 0 commits2026-03-27: 0 commits2026-03-28: 0 commits2026-03-29: 0 commits2026-03-30: 0 commits2026-03-31: 0 commits2026-04-01: 0 commits2026-04-02: 0 commits2026-04-03: 0 commits2026-04-04: 0 commits2026-04-05: 0 commits2026-04-06: 0 commits2026-04-07: 0 commits2026-04-08: 0 commits2026-04-09: 0 commits2026-04-10: 0 commits2026-04-11: 0 commits2026-04-12: 0 commits2026-04-13: 0 commits2026-04-14: 0 commits2026-04-15: 0 commits2026-04-16: 0 commits2026-04-17: 0 commits2026-04-18: 0 commits2026-04-19: 0 commits2026-04-20: 0 commits2026-04-21: 0 commits2026-04-22: 0 commits2026-04-23: 0 commits2026-04-24: 0 commits2026-04-25: 0 commits2026-04-26: 0 commits2026-04-27: 0 commits2026-04-28: 0 commits2026-04-29: 0 commits2026-04-30: 0 commits2026-05-01: 0 commits2026-05-02: 0 commits2026-05-03: 0 commits2026-05-04: 0 commits2026-05-05: 0 commits2026-05-06: 0 commits2026-05-07: 0 commits2026-05-08: 0 commits2026-05-09: 0 commits2026-05-10: 0 commits2026-05-11: 0 commits2026-05-12: 0 commits2026-05-13: 0 commits2026-05-14: 0 commits2026-05-15: 0 commits2026-05-16: 0 commits2026-05-17: 0 commits2026-05-18: 0 commits2026-05-19: 0 commits2026-05-20: 0 commits2026-05-21: 0 commits2026-05-22: 0 commits2026-05-23: 0 commits2026-05-24: 0 commits2026-05-25: 0 commits2026-05-26: 0 commits2026-05-27: 0 commits2026-05-28: 0 commits2026-05-29: 0 commits2026-05-30: 0 commits2026-05-31: 0 commits2026-06-01: 0 commits2026-06-02: 0 commits2026-06-03: 0 commits2026-06-04: 0 commits2026-06-05: 0 commits2026-06-06: 0 commits2026-06-07: 0 commits2026-06-08: 0 commits2026-06-09: 0 commits2026-06-10: 0 commits2026-06-11: 0 commits2026-06-12: 0 commits2026-06-13: 0 commits2026-06-14: 0 commits2026-06-15: 0 commits2026-06-16: 0 commits2026-06-17: 0 commits2026-06-18: 0 commits2026-06-19: 0 commits2026-06-20: 0 commits2026-06-21: 0 commits2026-06-22: 0 commits2026-06-23: 0 commits2026-06-24: 0 commits2026-06-25: 0 commits2026-06-26: 0 commits2026-06-27: 0 commits2026-06-28: 0 commits2026-06-29: 0 commits2026-06-30: 0 commits2026-07-01: 0 commits2026-07-02: 0 commits2026-07-03: 0 commits2026-07-04: 0 commits2026-07-05: 0 commits2026-07-06: 0 commits2026-07-07: 0 commits2026-07-08: 0 commits2026-07-09: 0 commits2026-07-10: 0 commits2026-07-11: 0 commits2026-07-12: 0 commits2026-07-13: 0 commits2026-07-14: 0 commits2026-07-15: 0 commits2026-07-16: 0 commits2026-07-17: 0 commits2026-07-18: 0 commits2026-07-19: 0 commits2026-07-20: 0 commits2026-07-21: 0 commits2026-07-22: 0 commits2026-07-23: 0 commits2026-07-24: 0 commits2026-07-25: 0 commits2026-07-26: 0 commits2026-07-27: 0 commits2026-07-28: 0 commits2026-07-29: 0 commits2026-07-30: 0 commits2026-07-31: 0 commits2026-08-01: 0 commits2026-08-02: 0 commits2026-08-03: 0 commits2026-08-04: 0 commits2026-08-05: 0 commits2026-08-06: 0 commits2026-08-07: 0 commits2026-08-08: 0 commits2026-08-09: 0 commits2026-08-10: 0 commits2026-08-11: 1 commit2026-08-12: 0 commits2026-08-13: 8 commits2026-08-14: 3 commits2026-08-15: 1 commit2026-08-16: 2 commits2026-08-17: 0 commits2026-08-18: 9 commits2026-08-19: 1 commit2026-08-20: 2 commits2026-08-21: 0 commits2026-08-22: 2 commits2026-08-23: 3 commits2026-08-24: 2 commits2026-08-25: 1 commit2026-08-26: 1 commit2026-08-27: 0 commits2026-08-28: 2 commits2026-08-29: 1 commit2026-08-30: 2 commits2026-08-31: 1 commit2026-09-01: 3 commits2026-09-02: 1 commit2026-09-03: 6 commits2026-09-04: 0 commits2026-09-05: 0 commits2026-09-06: 0 commits2026-09-07: 0 commits2026-09-08: 1 commit2026-09-09: 4 commits2026-09-10: 3 commits2026-09-11: 1 commit2026-09-12: 1 commit2026-09-13: 2 commits2026-09-14: 8 commits2026-09-15: 3 commits2026-09-16: 0 commits2026-09-17: 0 commits2026-09-18: 3 commits2026-09-19: 1 commit2026-09-20: 0 commits2026-09-21: 0 commits2026-09-22: 1 commit2026-09-23: 2 commits2026-09-24: 1 commit2026-09-25: 0 commits2026-09-26: 1 commit2026-09-27: 0 commits2026-09-28: 0 commits2026-09-29: 1 commit2026-09-30: 1 commit2026-10-01: 2 commits2026-10-02: 0 commits2026-10-03: 0 commits2026-10-04: 1 commit2026-10-05: 2 commits2026-10-06: 2 commits2026-10-07: 6 commits2026-10-08: 3 commits2026-10-09: 3 commits2026-10-10: 3 commits2026-10-11: 1 commit2026-10-12: 1 commit2026-10-13: 3 commits2026-10-14: 1 commit2026-10-15: 7 commits2026-10-16: 13 commits2026-10-17: 5 commits2026-10-18: 4 commits2026-10-19: 7 commits2026-10-20: 3 commits2026-10-21: 5 commits2026-10-22: 6 commits2026-10-23: 8 commits2026-10-24: 4 commits2026-10-25: 2 commits2026-10-26: 5 commits2026-10-27: 2 commits2026-10-28: 4 commits2026-10-29: 2 commits2026-10-30: 0 commits2026-10-31: 0 commits2026-11-01: 0 commits2026-11-02: 4 commits2026-11-03: 6 commits2026-11-04: 5 commits2026-11-05: 3 commits2026-11-06: 2 commits2026-11-07: 3 commits2026-11-08: 2 commits2026-11-09: 3 commits2026-11-10: 1 commit2026-11-11: 3 commits2026-11-12: 1 commit2026-11-13: 2 commits2026-11-14: 0 commits
226 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Widely adopted

    17,444 stars

  • Actively maintained

    Pushed within 48 hours

  • Permissive license

    Apache-2.0

  • Continuous integration

    Automated checks passing

  • Repeat trending

    6 trending appearances

What FreeToken does

FreeToken is a high-performance inference engine optimized for running massive Mixture-of-Experts models locally on consumer hardware. It treats heterogeneous edge resources like GPUs, CPUs, and system memory as a unified compute platform to handle models scaling up to 290 billion parameters. The engine utilizes advanced memory management, semantic caching, and bandwidth-adaptive co-execution to deliver blistering interactive speeds. It provides OpenAI-compatible APIs, allowing seamless integration with existing tools and frameworks.

AI enthusiasts, researchers, and developers with consumer GPU hardware. It is designed for users wanting to run massive MoE models without enterprise server equipment.

  • CPU-GPU co-execution: Adapts to hardware bandwidth to efficiently split inference tasks across available processors.
  • Semantic-aware caching: Avoids redundant recomputation by anchoring recurrent state and KV caches during agentic workflows.
  • Dynamic memory management: Re-allocates VRAM between expert caches and KV memory at runtime without restarting the engine.
  • Frontier MoE support: Runs massive open-weight models like DeepSeek-V4-Flash and Qwen3.6 across various quantization formats.
  • Standardized API: Exposes an Anthropic or OpenAI-compatible endpoint for easy drop-in replacement in existing apps.

Where teams use it

Local AI assistance

Run powerful LLMs entirely on a personal gaming PC for private, offline coding assistance.

Agentic workflow acceleration

Execute multi-step AI agent tasks efficiently using semantic caching to minimize context reprocessing.

Cost-free inference

Deploy high-quality MoE models locally to avoid the API costs associated with cloud-hosted frontier models.

Edge deployment

Serve capable AI models in environments with restricted internet access or strict data privacy requirements.

README

main branch
FreeToken

| Download | Paper | Developer Slack | Community Discord | Community WeChat |

Unlock datacenter-class intelligence on the hardware you already own — Run 290B+ frontier MoE models locally on your gaming PC at blistering interactive speeds.

About

FreeToken is an edge-native Mixture-of-Experts (MoE) serving engine designed for running frontier-scale open-weight models on personal and consumer hardware. It treats heterogeneous edge resources—GPUs, CPUs, host memory, and interconnects—as a unified, elastic inference platform. Its core features include:

  • Fast Edge-Native Runtime: Provides efficient MoE serving with bandwidth-adaptive CPU–GPU co-execution ($q^\star$ policy), full-layer double-buffered prefill streaming, global LRU expert caching, graph-compatible execution, and the FTW fast weight format.
  • Semantic-Aware Caching: Features semantic anchor checkpoints for recurrent state and KV caches, allowing agentic context edits (e.g., tool calls, thinking blocks) to avoid redundant context recomputation.
  • Elastic Memory Management: Supports dynamic, runtime VRAM re-allocation between expert caches and KV memory without engine restarts or weight reloading.
  • Broad MoE & Ecosystem Support: Supports frontier open-weight MoE models (e.g., DeepSeek-V4-Flash, Qwen3.6-35B-A3B, GLM-5.2) across various parameter scales and quantization formats (e.g., MXFP4, NVFP4, FP8, BF16, GGUF), with Anthropic/OpenAI-compatible APIs for seamless integration with real-world coding and tool-calling agents (e.g., Codex, Claude Code, OpenCode, OpenClaw, DeepSeek Harness).
  • Diverse Consumer Hardware: Scales across consumer laptops, gaming desktops, and workstation GPUs, with native support for NVIDIA RTX 30, RTX 40, and RTX 50 series GPUs.

Getting Started

Desktop app

Download FreeToken for Windows or Linux at flashml.ai. It sets the engine up for you and gives you a GUI for running models, chatting, and tuning the engine.

FreeToken Desktop

CLI

Install FreeToken with uv (recommended) or pip:

uv pip install "freetoken[accel]"

Or build from source:

git clone https://github.com/FlashML-org/FreeToken.git && cd FreeToken
uv venv && source .venv/bin/activate
uv pip install -e ".[accel]"

For More details:

Citation

If you use FreeToken for your research, please cite our paper:

@article{yang2026freetoken,
  title={FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution},
  author={Yang, Shuo and Fan, Xiaoze and Pan, Melissa and Xi, Haocheng and Wang, Zhe and Sun, Shanlin and Keutzer, Kurt and Han, Song and Zaharia, Matei and Xu, Chenfeng and Stoica, Ion},
  journal={arXiv preprint arXiv:2608.16157},
  year={2026}
}

Acknowledgment

FreeToken was deeply inspired by mini-sglang, and learned the design and reused code from the following projects: SGLang, vLLM, FlashInfer, flash-linear-attention, LightLLM and llama.cpp.

License

Apache License 2.0.

View on GitHub

Recent activity

commits and pull requests

Recent open issues

view all

Releases and announcements

6 total
  1. Nightly (rolling)nightlySep 9, 2026pre-release18 downloads

    ## FreeToken nightly (rolling) Automated build of `main`. This release is **overwritten every night**: the `nightly` tag moves to the built commit and the previous wheels are deleted. Do not pin to this tag; pin to a wheel URL below, whose filename embeds the commit it was built from. **Install** (Linux x86_64, CPython 3.12, CUDA 13.0): ```bash uv pip install \ "freetoken[accel] @ https://github.com/FlashML-org/FreeToken/releases/download/nightly/freetoken-0.2.2%2Bg66190a937-cp312-cp312-linux_x86_64.whl" \ "https://github.com/FlashML-org/FreeToken/releases/download/nightly/freetoken_kernel_cache-0.2.2%2Bcu130.g66190a937-py3-none-linux_x86_64.whl" ``` | commit | built (UTC) | python | cuda | runtime | kernel-cache | |---|---|---|---|---|---| | [`66190a937`](https://github.com/FlashML-org/FreeToken/commit/66190a937) | 2026-11-13 11:19 | cp312 | cu130 | 4.9 MB | 81.5 MB | <details><summary>sha256</summary> ``` f0b4e06d0d16d5d8d8337d863960e0ad8cfff32b29b3c6a8113ef45c239e9386 freetoken-0.2.2+g66190a937-cp312-cp312-linux_x86_64.whl 469daf4ac367842cdb16644ed6660778b2c9209ca8401fbe6f795f4962aa089f freetoken_kernel_cache-0.2.2+cu130.g66190a937-py3-none-linux_x86_64.whl ``` </det

  2. v0.2.2v0.2.2Nov 9, 2026285 downloads

    ## Highlights - **Speculative decoding.** `--speculative-algorithm mtp` drafts with the checkpoint's own MTP layer, and `--speculative-algorithm dflash` drafts with a separate DFlash 2 checkpoint (#836, #844, #856, #857). - **New model.** Ripple-65B Preview, from BF16 safetensors, the ModelOpt NVFP4 export or GGUF (#871). - **Faster CPU experts in `hybrid`.** The NVFP4 W4A8 CPU kernels are faster; rerun `ft bench bw` so `hybrid` uses the new CPU rate (#851). ## Speculative Decoding Each decode step drafts k tokens and verifies them on the target in one forward, so one step can commit several tokens. With sampling, the output distribution stays the target's. Speculative decoding is off by default, and the draft stays on the GPU, so it takes some KV and expert cache space. See the [flags](https://github.com/FlashML-org/FreeToken/blob/main/docs/cli.md#speculative-decoding). | Target | off | MTP (faster of k=3, k=7) | DFlash 2, k=7 | |---|---|---|---| | Qwen3.8-27B (BF16) | 50.1 | 144.4 (2.88x) | 215.0 (4.29x) | | Qwen3.6-35B-A3B (BF16) | 193.1 | 359.6 (1.86x) | 475.7 (2.46x) | | Qwen3.8-Flash-Next-NVFP4 | 92.9 | 149.7 (1.61x) | 174.2 (1.87x) | tok/s on an H100, on

  3. v0.2.1v0.2.1Oct 26, 2026716 downloads

    ## Highlights - [Feature] **Image input for GGUF models.** A llama.cpp mmproj file next to the model, or one passed with `--mmproj`, adds image input to Qwen3.5 / Qwen3.6 / Qwen3.8, Gemma-4, GLM-5.3-Flash and DeepSeek-V4-Flash-Vision-Exp GGUF files (#803, #810, #816). - [Feature] **More GGUF archs.** `deepseek4` (DeepSeek-V4 Flash, Flash-0731, Pro, Pro-0813) (#774), `qwen3vl` and `qwen3vlmoe` (text only) (#807). - [Feature] **Support Flint**, from BF16 safetensors, the ModelOpt NVFP4 export or the official NVFP4 GGUF (#797). - [Feature] **Embedding table in host RAM.** `--embed-weights host` keeps the input token embedding table in pinned host RAM and gives its VRAM to the expert cache and KV: decode is 8.7% faster on Qwen3.6-35B-A3B with 24 GiB of free VRAM (#806). ## GGUF Support - [Feature] **Image input from an mmproj file** (#803). llama.cpp keeps the vision tower in a separate `mmproj-*.gguf`. Without `--mmproj`, FreeToken takes a `*mmproj*.gguf` that fits the model (output width, tower type, image tokens) from the model file's own folder, BF16 before F32, F16 and quantized files; the log names the file it loads. With none, or with files of several models it canno

  4. v0.2.0v0.2.0Oct 21, 2026876 downloads

    ## Highlights - **GGUF Support.** llama.cpp GGUF files serve directly with `ft serve --model <local file>.gguf`; quantized tensors run on llama.cpp's own kernels (ggml-cuda on the GPU, ggml-cpu for `hybrid` / `cpu` experts). Supported GGUF archs: - `qwen2` (Qwen2 / Qwen2.5), `qwen3` and `qwen3moe` (Qwen3 dense and MoE) - `qwen35` and `qwen35moe` (Qwen3.5 / Qwen3.6 dense and MoE, Qwen3.8-27B), `qwen4exp` (Qwen3.8-Flash-Next) - `gemma4` (Gemma-4 12B, 26B-A4B, 31B) - `llama` (Llama 3.x, and Mistral files converted before llama.cpp's `mistral3` arch) - `muse-glimmer` (Muse-Glimmer) - `minimax-m2` (MiniMax-M2 / M2.x), `minimax-m3` (MiniMax-M3) - `glm4moe` (GLM-4.5, GLM-4.5-Air, GLM-4.6, GLM-4.7), `glm5-next` (GLM-5.3-Flash) - **Support new models.** - DeepSeek-V4.1-Flash, text and images (#603) - Image input for DeepSeek-V4-Flash-Vision-Exp (#502) - **Faster NVFP4 on sm_120 (RTX 50xx, RTX PRO Blackwell).** NVFP4 checkpoints with static activation scales run on NVFP4 activations (W4A4): at 128 or more tokens per expert the MoE layer is 2.54x faster on the RTX PRO 6000 and 3.72x on the RTX 5090 (#736), and Qwen3.8-27B-NVFP4 and Gemma-4-31B-IT-NVFP4 reach th

  5. v0.1.3v0.1.3Sep 16, 20262.9K downloads

    ## Highlights - **Image input.** Qwen3-VL, Qwen3.6, Qwen3.8-Flash-Next, Gemma-4, GLM-5.3-Flash, MiniMax-M3 and Muse-Glimmer-30B accept images through the OpenAI, Anthropic and Responses APIs. Vision towers stream their weights from host memory; `--text-model-only` serves a multimodal checkpoint as text. - **Support new models.** - Qwen3.8-Flash-Next (#257) - GLM-5.3-Flash (#332). - **Quantization rebuilt** (#418). One `QuantConfig` → `QuantScheme` → kernel path for every layer; kernels are selected with `--quant-backend layer[.kind]=name`, and `--moe-backend` becomes `--moe-strategy`. ## Multimodal FreeToken now serves vision-language models (#454): an image goes through the checkpoint's own processor and vision tower, then down the same scheduler, radix cache and MoE offload path as text. - **Engine**: image spans are content-keyed in the radix cache; encoded embeddings sit in an encoder cache between prefill chunks; the vision tower streams its weights from pinned host memory two blocks at a time. - **Server API**: OpenAI `image_url`, Anthropic image blocks and Responses `input_image` (URL, base64, `file://`); tool-result images are carried onto the next us

Code frequency

additions and deletions
+108.9K-108.9KWeek of 2026-08-09: +108,909 linesWeek of 2026-08-09: -345 linesWeek of 2026-08-16: +4,193 linesWeek of 2026-08-16: -259 linesWeek of 2026-08-23: +11,655 linesWeek of 2026-08-23: -318 linesWeek of 2026-08-30: +9,732 linesWeek of 2026-08-30: -547 linesWeek of 2026-09-06: +8,845 linesWeek of 2026-09-06: -6,784 linesWeek of 2026-09-13: +7,718 linesWeek of 2026-09-13: -764 linesWeek of 2026-09-20: +1,636 linesWeek of 2026-09-20: -741 linesWeek of 2026-09-27: +603 linesWeek of 2026-09-27: -187 linesWeek of 2026-10-04: +15,261 linesWeek of 2026-10-04: -1,904 linesWeek of 2026-10-11: +62,988 linesWeek of 2026-10-11: -13,065 linesWeek of 2026-10-18: +11,037 linesWeek of 2026-10-18: -991 linesWeek of 2026-10-25: +3,989 linesWeek of 2026-10-25: -1,673 linesWeek of 2026-11-01: +8,301 linesWeek of 2026-11-01: -2,866 linesWeek of 2026-11-08: +4,622 linesWeek of 2026-11-08: -685 linesAug 9, 2026Nov 8, 2026
+259.5K lines added, -31.1K removed over the last year.

Commits per week

last 52 weeks
370Week of 2025-11-16: 0 commitsWeek of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 0 commitsWeek of 2026-01-18: 0 commitsWeek of 2026-01-25: 0 commitsWeek of 2026-02-01: 0 commitsWeek of 2026-02-08: 0 commitsWeek of 2026-02-15: 0 commitsWeek of 2026-02-22: 0 commitsWeek of 2026-03-01: 0 commitsWeek of 2026-03-08: 0 commitsWeek of 2026-03-15: 0 commitsWeek of 2026-03-22: 0 commitsWeek of 2026-03-29: 0 commitsWeek of 2026-04-05: 0 commitsWeek of 2026-04-12: 0 commitsWeek of 2026-04-19: 0 commitsWeek of 2026-04-26: 0 commitsWeek of 2026-05-03: 0 commitsWeek of 2026-05-10: 0 commitsWeek of 2026-05-17: 0 commitsWeek of 2026-05-24: 0 commitsWeek of 2026-05-31: 0 commitsWeek of 2026-06-07: 0 commitsWeek of 2026-06-14: 0 commitsWeek of 2026-06-21: 0 commitsWeek of 2026-06-28: 0 commitsWeek of 2026-07-05: 0 commitsWeek of 2026-07-12: 0 commitsWeek of 2026-07-19: 0 commitsWeek of 2026-07-26: 0 commitsWeek of 2026-08-02: 0 commitsWeek of 2026-08-09: 13 commitsWeek of 2026-08-16: 16 commitsWeek of 2026-08-23: 10 commitsWeek of 2026-08-30: 13 commitsWeek of 2026-09-06: 10 commitsWeek of 2026-09-13: 17 commitsWeek of 2026-09-20: 5 commitsWeek of 2026-09-27: 4 commitsWeek of 2026-10-04: 20 commitsWeek of 2026-10-11: 31 commitsWeek of 2026-10-18: 37 commitsWeek of 2026-10-25: 15 commitsWeek of 2026-11-01: 23 commitsWeek of 2026-11-08: 12 commitsNov 16, 2025Nov 8, 2026
226 commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 0 commitsSun 1:00 — 1 commitsSun 2:00 — 0 commitsSun 3:00 — 1 commitsSun 4:00 — 0 commitsSun 5:00 — 0 commitsSun 6:00 — 0 commitsSun 7:00 — 0 commitsSun 8:00 — 1 commitsSun 9:00 — 0 commitsSun 10:00 — 1 commitsSun 11:00 — 1 commitsSun 12:00 — 0 commitsSun 13:00 — 1 commitsSun 14:00 — 2 commitsSun 15:00 — 1 commitsSun 16:00 — 0 commitsSun 17:00 — 3 commitsSun 18:00 — 0 commitsSun 19:00 — 0 commitsSun 20:00 — 1 commitsSun 21:00 — 0 commitsSun 22:00 — 2 commitsSun 23:00 — 4 commitsMon 0:00 — 0 commitsMon 1:00 — 0 commitsMon 2:00 — 0 commitsMon 3:00 — 3 commitsMon 4:00 — 0 commitsMon 5:00 — 0 commitsMon 6:00 — 0 commitsMon 7:00 — 0 commitsMon 8:00 — 2 commitsMon 9:00 — 1 commitsMon 10:00 — 0 commitsMon 11:00 — 2 commitsMon 12:00 — 1 commitsMon 13:00 — 2 commitsMon 14:00 — 2 commitsMon 15:00 — 2 commitsMon 16:00 — 1 commitsMon 17:00 — 2 commitsMon 18:00 — 1 commitsMon 19:00 — 1 commitsMon 20:00 — 4 commitsMon 21:00 — 4 commitsMon 22:00 — 2 commitsMon 23:00 — 3 commitsTue 0:00 — 1 commitsTue 1:00 — 1 commitsTue 2:00 — 0 commitsTue 3:00 — 0 commitsTue 4:00 — 0 commitsTue 5:00 — 1 commitsTue 6:00 — 1 commitsTue 7:00 — 0 commitsTue 8:00 — 1 commitsTue 9:00 — 1 commitsTue 10:00 — 0 commitsTue 11:00 — 0 commitsTue 12:00 — 2 commitsTue 13:00 — 3 commitsTue 14:00 — 2 commitsTue 15:00 — 4 commitsTue 16:00 — 4 commitsTue 17:00 — 1 commitsTue 18:00 — 2 commitsTue 19:00 — 3 commitsTue 20:00 — 6 commitsTue 21:00 — 1 commitsTue 22:00 — 1 commitsTue 23:00 — 2 commitsWed 0:00 — 3 commitsWed 1:00 — 0 commitsWed 2:00 — 1 commitsWed 3:00 — 1 commitsWed 4:00 — 0 commitsWed 5:00 — 1 commitsWed 6:00 — 0 commitsWed 7:00 — 0 commitsWed 8:00 — 1 commitsWed 9:00 — 0 commitsWed 10:00 — 1 commitsWed 11:00 — 3 commitsWed 12:00 — 1 commitsWed 13:00 — 3 commitsWed 14:00 — 3 commitsWed 15:00 — 1 commitsWed 16:00 — 1 commitsWed 17:00 — 1 commitsWed 18:00 — 1 commitsWed 19:00 — 1 commitsWed 20:00 — 2 commitsWed 21:00 — 1 commitsWed 22:00 — 4 commitsWed 23:00 — 4 commitsThu 0:00 — 1 commitsThu 1:00 — 2 commitsThu 2:00 — 0 commitsThu 3:00 — 1 commitsThu 4:00 — 0 commitsThu 5:00 — 0 commitsThu 6:00 — 0 commitsThu 7:00 — 0 commitsThu 8:00 — 0 commitsThu 9:00 — 0 commitsThu 10:00 — 2 commitsThu 11:00 — 2 commitsThu 12:00 — 0 commitsThu 13:00 — 4 commitsThu 14:00 — 3 commitsThu 15:00 — 1 commitsThu 16:00 — 6 commitsThu 17:00 — 6 commitsThu 18:00 — 3 commitsThu 19:00 — 1 commitsThu 20:00 — 4 commitsThu 21:00 — 1 commitsThu 22:00 — 1 commitsThu 23:00 — 6 commitsFri 0:00 — 2 commitsFri 1:00 — 0 commitsFri 2:00 — 0 commitsFri 3:00 — 1 commitsFri 4:00 — 0 commitsFri 5:00 — 0 commitsFri 6:00 — 1 commitsFri 7:00 — 3 commitsFri 8:00 — 1 commitsFri 9:00 — 0 commitsFri 10:00 — 1 commitsFri 11:00 — 1 commitsFri 12:00 — 4 commitsFri 13:00 — 2 commitsFri 14:00 — 3 commitsFri 15:00 — 5 commitsFri 16:00 — 2 commitsFri 17:00 — 4 commitsFri 18:00 — 1 commitsFri 19:00 — 2 commitsFri 20:00 — 0 commitsFri 21:00 — 0 commitsFri 22:00 — 2 commitsFri 23:00 — 2 commitsSat 0:00 — 2 commitsSat 1:00 — 0 commitsSat 2:00 — 0 commitsSat 3:00 — 0 commitsSat 4:00 — 2 commitsSat 5:00 — 1 commitsSat 6:00 — 1 commitsSat 7:00 — 0 commitsSat 8:00 — 1 commitsSat 9:00 — 0 commitsSat 10:00 — 0 commitsSat 11:00 — 0 commitsSat 12:00 — 3 commitsSat 13:00 — 3 commitsSat 14:00 — 0 commitsSat 15:00 — 0 commitsSat 16:00 — 1 commitsSat 17:00 — 1 commitsSat 18:00 — 0 commitsSat 19:00 — 0 commitsSat 20:00 — 0 commitsSat 21:00 — 2 commitsSat 22:00 — 1 commitsSat 23:00 — 4 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Nov 3, 2026daily#3+654
Nov 2, 2026daily#3+654
Nov 1, 2026daily#9+232
Sep 23, 2026monthly#9+13,373
Sep 22, 2026monthly#9+13,373
Sep 21, 2026monthly#2+13,363