#Open source/Repo

AIIndexTeam released Index-Homura-2B-FP4, an official NVFP4 (W4A4) quantization of its Index-Homura-2B multilingual translation model, which supports 150 languages. The quantized checkpoint shows a 5.73% perplexity increase over the BF16 original (3.5011 to 3.7017) on a fixed corpus, and its zh-en and en-zh outputs are semantically equivalent under greedy decoding. Full FP4 acceleration requires an NVIDIA Blackwell GPU, while the source recommends the FP8 build for Hopper and Ampere hardware.

AIAleph Alpha has released Kolibri, a model with 78B total parameters, 3.46B active, and up to 1M tokens of context, under Apache 2.0. The quoted post says the weights can be run on the user's own hardware. Cohere's own post is a short endorsement of the release.

AIAMD has reached above 90% parity on upstream vLLM gating test groups this week, according to SemiAnalysis. The milestone followed months of work by AMD maintainers, including Andreas, and vLLM CI lead Kevin, plus SemiAnalysis supplying additional AMD GPUs to vLLM CI.

AIAlephAlpha has released Kolibri, a German-English model with 78B total parameters, 3.46B active, and context up to 1M tokens. The weights are available under Apache 2.0 for running on users' own hardware. Cohere's Aidan Gomez congratulated the team on the model and its detailed technical report.

AIAMD made 502 commits to core vLLM over 90 days, accounting for 13% of all organizational contributions and almost four times Nvidia's count. The company credited Red Hat, IBM, Embedded LLM, and Inferact for building the project alongside it.

AIPixVerse shares a link to a plugin for its CLI aimed at marketing use. The post provides no further details on features, pricing, or availability.

AIThe creator Khazix open-sourced AIHOT, a monthly-active-million AI hot-news site, including its collection workflow, curation scoring, clustering mechanism, and production prompts. The main post reports the project gained 5.1K GitHub stars within a few days and thanks supporters on X.

AIOpenClaw v2026.9.8 is released with support for GPT-6.1 Sol, agent replies that return to their original conversation, and lower memory use. The release also includes update and Windows startup fixes, covering 43 PRs from 8 contributors.

AIvLLM Semantic Router has released Decision 2.0, featuring open models ranging from 0.6B to 27B parameters. The models can answer 64 questions about a request in a single forward pass, are licensed under Apache-2.0, and load with Transformers.

AIOllama now offers Cloudflare's decision models, Clef (27B) and Clef Flash (9B), which classify images, label bug reports, and route support tickets. Users can run them locally with the commands ollama pull clef and ollama pull clef-flash.

AIOllama has published Clef Flash and Clef as new models in its model library, with links to their library pages. The post provides no further details on parameters, benchmarks, or capabilities.

AINVIDIA's Nemotron 3 Diarization model identifies who spoke when, including during overlapping speech, and is now available on Hugging Face. It supports up to eight speakers and has 100M parameters. The post thanks users for downloads and trending activity and shares a follow-up answering community questions.

AIPrime Intellect says its production stack now processes roughly 600B tokens daily on its own compute. The company also states its GLM-5.3 deployment ranks among the fastest GLM-5.3 endpoints on OpenRouter.

AIMuse has released Muse Gadgets, an open-source ESP32 firmware and Linux SDK for building hardware devices that work with Muse. Developers can obtain an API token from gadgets.muse.ai and use a coding agent with the GitHub repo to build peripherals. Guillermo Rauch praised the team's rapid shipping.

AIPerplexity has released several open source projects, including the pplx-decider-v1-27b multimodal decision model, the pplx-embed-v2-context-9b-preview contextual embeddings model, and the Lily local inference engine for Apple silicon. The post also lists the 0.6B on-device PII-Tracer classifier with its PII-TRACE benchmark, the WANDR research agent benchmark, and the Numbat and Bumblebee security tools, and says more open source releases are coming soon.

AIxAI has published an early version of its TypeScript SDK, available on GitHub at xai-org/xai-sdk-ts and on npm as @xai-official/sdk. The post invites developer feedback as the company continues iterating on it.

AIxAI has released an experimental TypeScript SDK, installable via npm install @xai-official/sdk, that covers text, voice, image, and video in one package. It provides access to the latest Grok models along with server-side tools including real-time X search, web search, code execution, and remote MCP.

AIDatabricks' new open-source meta-harness, Omnigent, lets multiple coding agents such as Claude Code and Codex share sessions, rules, and security policies in one system. A walkthrough by @leonvz demonstrates forking work across agents, multi-agent review and debate with Debby, and splitting implementation across subagents with Polly.

AIKeras is moving to a pluggable backend design, with MLX and PaddlePaddle backends upcoming as add-on libraries. The team is reducing the operations needed to ship new backends and streamlining unit testing so a single harness can test all ops, such as casting consistency. KerasHub also gains many new models and is shifting its preprocessing from tf-text to PyGrain.

AITypeSafe AI shows how to build long-document search by combining its Jev with PageIndex, with no vector database or embeddings required. The project is open source on GitHub under VectifyAI's jev-doc-search repository.

AIOpenCode is offering inclusionAI's latest model, Ling-3.1-flash, for free. The model has 560B total parameters, 25B active parameters, and a 262K context window.

AIAnt Ling has made Ling-3.1-flash available on OpenRouter at no cost, inviting users to try it and share feedback. The post provides no details on model size, benchmarks, context length, or pricing beyond the free access.

AIAi2 released AstaBrief 8B, an open-weights model that turns a research question and retrieved literature excerpts into a cited report, along with its training data. The model runs as Fast mode in Asta, averaging 51.1 seconds per report versus 178.5 seconds for Thinking mode, about 3.5x faster. The post also describes filtering synthetic training data by citation density and building DPO pairs judged by two models that agreed.

Why it matters: The post explains how supervised fine-tuning, preference data, and citation-density filtering were used to build a cited-report model, which is useful for teams training their own models.

AILiquid AI shared a Hugging Face guide to multi-harness reinforcement learning for coding agents, in which a proxy records the token ids and logprobs vLLM samples so training works without changing the harness. Per the quoted post, LFM2.5-2.6B rose from 42% to 54% after training across four harnesses at once, and imitation fine-tuning on 3,189 rollouts from Qwen3.8-27B plateaued at 47.5%, below both RL runs. The proxy, trainer, tasks, SFT data, training code and seven trained models are described as open.

AIGoogle announces a next-generation federated learning system that uses Trusted Execution Environments to provide verifiable, auditable data anonymization. The system publishes access policies to a public transparency log and is deployed in Gboard, which has launched English and Japanese next-word prediction models with stronger privacy guarantees and improved accuracy. Training time has also sped up significantly because computation moved to the server and is parallelized across many machines.

Why it matters: The post shows how Trusted Execution Environments make federated learning's privacy claims externally verifiable, rather than relying on trust in the server operator.

AIllama.cpp now supports decision models, which route tickets, moderate content, or choose an agent's next step by returning a probability for every option. Five open models from 144M to 27B parameters are supported at launch, and the team says more will follow in the coming days. Because most decision models do not need large GPUs, they are a good fit for llama.cpp, and a Hugging Face blog post explains how to set them up.

AIGeorgi Gerganov announced that decision models are now available in the latest llama.cpp builds through a new /v1/systemone endpoint. The endpoint supports local, private inference with multiple open models, and more are planned.

AIinclusionAI has released Ling 3.1 Flash, a hybrid reasoning mixture-of-experts model with 560B total parameters, of which 25B are active. The source does not provide benchmark scores, pricing, context length, or availability details.

AIAi2 released AstaBrief 8B, a model that turns a research question and retrieved literature excerpts into a cited report, along with its training data. In Asta's Generate a report feature, Fast mode averages 51.1 seconds per report versus 178.5 seconds for Thinking mode, about 3.5x faster. The model is built on Qwen3-8B with supervised fine-tuning and DPO, and institutions can run its open weights on their own infrastructure.

Why it matters: The post explains the data filtering and one-pass generation choices behind a fast open-weights report model, showing what worked and what did not.

AIDeepSeek released packaged desktop versions of DeepSeek Harness for macOS and Windows. Linux users can install it from the @deepseek-ai/dsh package on npm.

AITeknium, back from vacation, says the Hermes update should be around 4x faster for everyone. The post gives no further details on what changed or how the speedup was measured.

AIcheap typed answers for the small calls inside a harness (routing, approvals, judging), big model for the rest

AIPerplexity open-sourced pplx-decider-27b, a state-of-the-art multimodal Decision Model, and offers it through a new Decisions API. Input tokens cost $0.04 per million and output tokens are free, with further price cuts promised in the coming days.

AIARC Prize has published full ARC-AGI results for Alibaba's Qwen3.8-27B, with the testing run hosted by Baseten. The post links the public leaderboard, the open-source benchmarking repository for reproducing the results, and the testing policy.

AIGuillermo Rauch argues that the future is verification engineering, spanning proofs, end-to-end tests, benchmarks, and linters. He expects some of these tests to be deterministic and others agentic, and he says the approach looks great. The quoted post introduces e2e, an open-source agentic testing framework that mixes deterministic and agentic APIs and runs locally or in CI.

AIAnthropic is adding pre-built sample mods to the Claude Code Playground repo for developers to adapt. The post points readers to a getting started guide on creating Claude Code mods.

AICloudflare has open-sourced Clef and Clef-Flash, its first homegrown decision models, now available on Workers AI. Harrison Chase praised the release as an open-weights entrant and argued that agent harnesses should be able to swap their decision model as easily as their main model.

AIGitHub Security Lab has released gh-secure, a tool that gives repositories basic security hygiene with a single command to help stop secrets from leaking into public code. It can be installed and used in the Copilot app, Copilot CLI, or GitHub CLI.

AIGoodfire says AI cybersecurity risks are already here and that biosecurity risks are next, as models improve at biology. The post presents this as both an opportunity for science and medicine and a reason for stronger security. It quotes Demis Hassabis announcing SynthID for biology, a watermarking approach for AI-generated proteins, published in Nature with SynthID Bio tools open sourced.