Skip to contentSkip to stories
Updated
#Open-source ecosystem

#Open-source ecosystem

Oct 9

Oct 9Fri
  1. PandailyNewsAI score59

    MirroS open-sources AgentGarten, a framework where AI agents learn in live-rendered code worlds

    AIMirroS has released AgentGarten, an open framework where AI agents act, observe and learn in simulated worlds. Code handles physics and game rules, while a neural renderer turns geometry sketches into realistic frames at more than 30 frames per second at 480p on a single GPU. Across five worlds, agents improved over rounds using a playbook of lessons, such as a companion-dog score rising from 13 to 19. The team describes it as a research environment, not a deployed robot product.

  2. RadixArkOfficialAI score60

    RadixArk's Miles runs end-to-end RL on NVIDIA Vera Rubin with SGLang

    AIRadixArk says Miles runs reinforcement learning end to end on NVIDIA Vera Rubin, using SGLang rollouts, Megatron training and one container image. Agentic RL runs 64 concurrent sandboxes on the Vera CPU next to the GPUs. The linked SGLang post reports that Kimi K3 inference gained up to 20% faster FP8 MLA at batch 1 with 128K context, and a 5.9% end-to-end speedup from MoE tail fusion.

    Why it matters: The post gives concrete speedup figures and a specific RL setup on early-access Rubin hardware, useful for engineers comparing inference and training stacks.

  3. vLLM BlogOfficialAI score62

    vLLM adds support for NVIDIA Vera Rubin NVL72 with 7.8x throughput over GB200

    AIvLLM now supports NVIDIA Vera Rubin NVL72, with daily container builds and support for models from DeepSeek, Moonshot AI, Z.ai, and MiniMax. In early AgentX benchmarks, vLLM running MiniMax M3 delivered up to 7.84x the throughput per GPU of GB200 NVL72 at matched interactivity. The post is an early look, and the team expects further gains from ongoing optimizations.

    Why it matters: The post gives specific hardware specs, kernel configurations, and benchmark figures for running vLLM on Vera Rubin NVL72, useful for teams planning deployments.

  4. MarkTechPostNewsAI score44

    Underdog Releases Saluki 27B, a 2-Bit Qwen3.8-27B That Beats the Original at Tool Calling

    AIUnderdog has released Saluki 27B under Apache 2.0, a 2-bit GGUF of Qwen3.8-27B that fits in 7.89 GB, versus 54 GB for the full BF16 model. On Underdog Bench, Saluki scores 88 against 84 for the full model, and it raises parallel tool-call accuracy to 42 from 35. It runs on stock llama.cpp, but math and reasoning drop sharply, with AIME 2025 at 79.2 versus 96.7.

Oct 8

Oct 8Thu
  1. meng shaoXAI score77

    Theo open-sources tsc-rs, a Rust port of the TypeScript 7 compiler

    AITheo, creator of the T3 Stack, open-sourced tsc-rs, a line-by-line Rust port of Microsoft's Go-native TypeScript 7 compiler, type checker, and language server under MIT, pinned to typescript-go commit 673a5f17. The author reports tsc-rs is about 1.61× faster than tsc 7 and about 2.95× faster than bun check on six real-app benchmarks on an Apple M4 Pro. The port passes all 181,711 ported Go tests, and CLI output matches the Go version on 120 open-source repos except for known edge cases such as monorepo rootDir and tsc -b incremental output.

    Why it matters: The post reports a benchmarked, test-verified Rust port of the TypeScript 7 compiler, with pinned upstream and stated edge cases useful for judging its compatibility.

    Image from @shao__meng's post
  2. Hacker News · Show HN, AI (20+ points)BlogAI score62

    Rembrandt releases a free, open-source local photo editor with on-device AI

    AIRembrandt is a free, open-source photo editor for macOS, Windows and Linux that runs locally and needs no account or subscription. It saves edits as standard XMP sidecar files next to each photo and can also run as a self-hosted server accessed through a browser. Only optional cloud sync is paid.

  3. elvisXAI score42

    Voyager: an open harness for creative AI work across video and games

    AIElvis Saravia argues that creative work needs domain-specific agent harnesses rather than coding-oriented ones, and he highlights Voyager as an open harness for video, graphics, and games. According to the quoted post, Voyager lets agents work with local files and drive apps such as Blender, DaVinci Resolve, and Unity, and it is designed to work with models like Opus, Astra, and DeepSeek.

    Video from @omarsar0's post
  4. Alexander DoriaXAI score46

    LightOnOCR-3 claims state-of-the-art OCR performance under 1B parameters

    AILightOn has released LightOnOCR-3, a family of OCR models in 0.8B and 4B versions that it says lead benchmarks including OlmOCR-Bench and ParseBench, with the 0.8B model positioned as the sub-1B option. The models recognize text, handwriting, images, charts and document structure in one pass, process documents up to twice as fast as LightOnOCR-2, and are released under the Apache 2.0 license.

    Image from @Dorialexander's post
  5. Dhravya ShahXAI score42

    MemoryRepo: open-source implementation of Cognition's dreaming agent memory

    AISupermemory introduces MemoryRepo.dev, an open-source implementation of Cognition's dreaming memory system built on Cloudflare Artifacts, Durable Objects, Alchemy, and Effect. The project follows Cognition's Devin memory design, which builds a memory graph across sessions and prunes stale records overnight. Supermemory says it will incorporate learnings from this research into its own product.

    Video from @DhravyaShah's post

Oct 7

Oct 7Wed
  1. Ars Technica · AINewsAI score46

    Artcraft releases open source clones of Adobe Photoshop, Premiere and other apps built with Claude

    AIDeveloper Brandon Thomas's Artcraft has launched seven open source apps in Rust that aim to replicate the interfaces and tools of Adobe Photoshop, Illustrator, Premiere, Lightroom, After Effects, InDesign, and Acrobat Pro. Thomas said he used Anthropic's Claude Opus 5.5 to build the clean-room replacements, with WebAssembly versions available for browser use. The apps remain in a "super early alpha" state, and commenters have pointed out many current shortcomings.

  2. LlamaIndex 🦙OfficialAI score47

    LlamaIndex launches OpenDocRouter, one API for many document parsing models

    AILlamaIndex announced OpenDocRouter, a single API that routes document parsing requests to any of 10 frontier and open-source models at launch, including Claude Opus 5.5, Gemini 3.8 Flash, GPT-6 Luna, MinerU2.5-Pro, and PaddleOCR-VL-1.6. Users can switch models in one line with the same request and markdown output, and each model is scored on ParseBench for quality and cost. Pricing is per-token, failed pages are not charged, and the service costs $0.86 to $48.82 per 1,000 pages depending on the model.

    Video from @llama_index's post

Oct 6

Oct 6Tue
  1. Epoch AIOfficialAI score47

    GPT-6 Astra Hit 100% on EBR-bench Using a Card That Bypassed Its Time Limits

    AIEpoch AI reports that GPT-6 Astra scored 100% on the original EBR-bench by exploiting a card that bypasses the game's time-constraint expectations, so Epoch has banned that card from the default setting. Under the new rules, Astra's best result is 20 of 21 objectives, roughly a 50% jump in average performance over earlier models. Epoch will report revised scores only for Claude Fable 5.1, Claude Opus 5, GPT-5.6 Sol, GPT-6 Astra, and future models.

  2. SGLangOfficialAI score62

    SGLang adds support for Kandinsky 6.0 Video audio-visual generation

    AISGLang now supports Kandinsky 6.0 Video, which generates video and synchronized audio together from text or an image. The model comes in Lite (3B) and Pro (29B) sizes, with built-in super-resolution up to 1920×1080. A sample sglang serve command for the Pro distilled model is included.

    Why it matters: The post shows the exact serve command and model size options, which lets engineers judge whether this open video model fits their hardware and pipeline.

    Image from @sgl_project's post

Sep 30

Sep 30Wed
  1. Comfy BlogOfficialAI score60

    Comfy API launches to deploy ComfyUI workflows as autoscaling endpoints

    AIComfy API is now available to all users on a paid Comfy plan, letting them package a ComfyUI workflow with its custom nodes, LoRAs, models, and Python dependencies and deploy it as an autoscaling API endpoint. Builds capture the ComfyUI version and dependencies, and each immutable release gets its own URL, so the tested environment is the deployed one. Usage is billed separately, with GPU time charged by the second and storage prorated hourly.

    Why it matters: The post explains how a ComfyUI workflow is packaged into immutable releases and deployed as an autoscaling endpoint, showing a path from local graph to production service.

  3. ModelScopeOfficialAI score46

    IndexTeam releases Index-Translate multilingual translation model family

    AIIndexTeam has released Index-Translate, a multilingual family covering text, speech, dubbing, and long-document translation across 150 languages. Its 9B model scores 0.8789 on FLORES, 0.8209 on instTrans, and 0.7387 on MEME, and the 2B and 9B models are released under Apache 2.0.

    Video from @ModelScope2022's post

Sep 29

Sep 29Tue
  1. OpenClaw🦞OfficialAI score70

    OpenClaw Enterprise launches as an open-source control plane for persistent agents

    AIThe OpenClaw Foundation announced OpenClaw Enterprise, an open-source enterprise control plane for persistent agents, in collaboration with Red Hat, NVIDIA, and OpenAI. The product is built to run on an organization's own infrastructure and will always be free for organizations to use.

    Why it matters: The announcement names its collaborators and deployment model, which helps organizations judge how the enterprise control plane would fit their own infrastructure.

    Image from @openclaw's post
  2. ModelScopeOfficialAI score54

    IQuest-Q1 released as 320B MoE model for long-horizon coding agents

    AIModelScope announced IQuest-Q1, a 320B MoE model with 15B active parameters and a 512K context window for agentic coding. The post reports scores of 84.5 on CyberGym, 83.2 on Terminal-Bench 2.1, 64.6 on DeepSWE v1.1, and 63.0 on NL2Repo, and says weights are released under the IQuest-Q1 License.

    Image from @ModelScope2022's post

Sep 28

Sep 28Mon
  1. ModelScopeOfficialAI score46

    Qwen-Image-2.1 LoRAs extract and remove layers for editing

    AIModelScope released two Qwen-Image-2.1 LoRAs, LayerExtract and LayerRemove, for layer-based image editing. LayerExtract isolates a prompt-specified subject onto a transparent background, while LayerRemove deletes the matching object from the source image and reconstructs the scene behind it. Both can be hot-swapped within the same DiffSynth-Studio pipeline, and the LoRA weights are licensed under Apache 2.0, with Qwen-Image-2.1 base-model terms also applying.

    Image from @ModelScope2022's post