Skip to content

Open systems / 03

Open-source releases worth evaluating.

Find new AI tools and meaningful releases with source links, adoption context, and practical tradeoffs.

  1. api7/aisix

    Open-source AI gateway for LLMs & AI agents, built in Rust. One OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock & more — routing, guardrails, caching, rate limits, observability.

    github.com5 months ago22 ptsView details

  2. ggml-org/llama.cpp b10472

    <details open> cuda : skip UMA override for HIP builds (#27083) AMD APUs report accurate memory via hipMemGetInfo. Using MemAvailable over-promises on small-carveout systems. fixes #18159 </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)…

    github.com1 month agoView details

  3. bergside/awesome-design-skills

    List of 67 awesome DESIGN.md and SKILL.md design skill files for agentic tools like Claude Design, Google Stitch, Codex, Cursor, and other AI tools

    github.com6 months ago34 ptsView details

  4. aiptimizer/TurboOCR

    TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

    github.com6 months ago30 ptsView details

  5. F-R-L/forge-film

    Multi-model DAG-driven parallel AI film generation — parallel speedup scales with scene independence; Generate film scenes simultaneously instead of one by one; "把影视生成的执行图从拓扑序变成关键路径最优调度" ; 唯一把场景叙事依赖建模为 DAG、以 CPM 算法驱动并行调度的影视生成引擎

    github.com5 months ago28 ptsView details

  6. ggml-org/llama.cpp b10470

    <details open> ci : push release tag explicitly in release.yml (#27261) Add a "Create and push git tag" step to the release job, right before the "Create release" step. The tag is created with git tag and pushed with the deploy key already configured by the Clone step, instead o…

    github.com1 month agoView details

  7. 0xMassi/webclaw

    Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.

    github.com6 months ago34 ptsView details

  8. ggml-org/llama.cpp b10456

    <details open> sycl: fix thread/block count in quantized cpy kernel launches (#27160) Adjusts the thread/block count to be proportional to the size of the quant, reducing under/over subscription. Largest perf improvement is the q4_0 -> f32 path, with, on a Arc 70, throughput goe…

    github.com1 month agoView details

  9. ggml-org/llama.cpp b10455

    <details open> [SYCL] support OP OPT_STEP_ADAMW, OPT_STEP_SGD (#25268) * fix conflict * fix conflict of ops.md * fix conflict of ops.md * update the ops.md --------- Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com> </details> **Website:** - <https://llama.app> **macOS/i…

    github.com1 month agoView details

  10. jundot/omlx

    LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

    github.com7 months ago43 ptsView details

  11. NateBJones-Projects/OB1

    Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS.

    github.com6 months ago37 ptsView details

  12. millionco/react-doctor

    Your agent writes bad React. This catches it

    github.com7 months ago42 ptsView details

  13. heymrun/heym

    Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.

    github.com5 months ago31 ptsView details

  14. Thysrael/Horizon

    📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达

    github.com7 months ago40 ptsView details

  15. ggml-org/llama.cpp b10453

    <details open> model : remove some ggml_concat (#27176) Co-authored-by: Xuan Son Nguyen <son@huggingface.co> </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10453/llama-b10453-b…

    github.com1 month agoView details

  16. yantrikos/yantrikdb-server

    Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, Apache-2.0, ships as library / MCP server / HTTP cluster.

    github.com5 months ago22 ptsView details

  17. astrid-runtime/astrid

    Astrid is a portable, capability-secure operating system for composable software.

    github.com7 months ago40 ptsView details

  18. ggml-org/llama.cpp b10451

    <details open> llama : check LoRA tensor data is within file bounds (#27056) * llama : check LoRA tensor data is within file bounds * Update src/llama-adapter.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigb…

    github.com1 month agoView details

  19. Lightricks/LTX-Desktop

    An open-source desktop app for generating videos with LTX models

    github.com6 months ago33 ptsView details

  20. Runfusion/Fusion

    Your Software Factory - build faster and better with multi node agents that work 24/7

    github.com5 months ago31 ptsView details

  21. CortexReach/memory-lancedb-pro

    Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI

    github.com6 months ago36 ptsView details

  22. giancarloerra/SocratiCode

    Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra…

    github.com6 months ago35 ptsView details

  23. cactus-compute/needle

    14MB foundation model for tiny devices; phones, wearables, smart home, and robots.

    github.com6 months ago39 ptsView details

  24. ggml-org/llama.cpp b10448

    <details open> model: add Kimi-K3 text model (#26185) * model: add Kimi-K3 text model Hybrid KDA (linear) + MLA (full) attention as in Kimi-Linear-48B, plus five things that architecture does not have: 1. cross-layer residual attention (attn_res_block_size) 2. latent MoE (routed…

    github.com1 month agoView details

  25. taco-group/SparkVSR

    [ECCV 2026] SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation

    github.com6 months ago28 ptsView details

  26. NVIDIA/skills

    Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

    github.com6 months ago35 ptsView details

  27. ggml-org/llama.cpp b10447

    <details open> server: re-design yield_to_queue thread model (#27133) * run common_speculative_process in worker * swap worker <--> main thread design </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.c…

    github.com1 month agoView details

  28. open-gitagent/opengap

    A framework-agnostic, git-native standard for defining AI agents

    github.com6 months ago35 ptsView details

  29. RunanywhereAI/RCLI

    Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG

    github.com6 months ago32 ptsView details

  30. voocel/ainovel-cli

    ✨多agent实现全自动AI小说生成

    github.com6 months ago33 ptsView details

  31. vasu-devs/JustHireMe

    Local-first AI job intelligence workbench for scraping roles, ranking fit, and generating tailored application materials.

    github.com6 months ago33 ptsView details

  32. ggml-org/llama.cpp b10437

    <details open> model : add support for MiniMaxText01ForCausalLM and MiniMaxM1ForCausalLM (#27018) * llama : support for MiniMax-Text-01 model * chore : renames to match the other MiniMax models * model : add logits mask as MiniMax-Text-01 embeddings tensor has zero-valued embedd…

    github.com1 month agoView details

  33. ggml-org/llama.cpp b10436

    <details open> mtmd, common: various fixes (#27071) * apply fixes * cont * revert gguf fix </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10436/llama-b10436-bin-macos-arm64.tar…

    github.com1 month agoView details

  34. nambok/mentedb

    A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.

    github.com5 months ago21 ptsView details

  35. openai/openai-python v3.1.0

    ## [3.1.0](https://github.com/openai/openai-python/compare/v3.0.0...v3.1.0) (2026-08-14) ### Features * **api:** add WebSocket stream IDs ([#3612](https://github.com/openai/openai-python/issues/3612)) ([d9029e3](https://github.com/openai/openai-python/commit/d9029e3ada3c008b4631…

    github.com1 month agoView details

  36. ggml-org/llama.cpp b10435

    <details open> jinja : fix quadratic cost in gather_string_parts (#27034) * jinja : fix quadratic cost in gather_string_parts * fix some comments * remove test </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-or…

    github.com1 month agoView details

  37. builderz-labs/mission-control

    Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes.

    github.com7 months ago38 ptsView details

  38. langchain-ai/langchain langchain-openrouter==0.2.8

    Changes since langchain-openrouter==0.2.7 release(openrouter): 0.2.8 (#39658) chore(model-profiles): refresh model profile data (#39646) chore(model-profiles): refresh model profile data (#39625) fix(openrouter): preserve cost metadata in usage chunks (#39338) chore(model-profil…

    github.com1 month agoView details

  39. langchain-ai/langchain langchain-core==1.5.5

    Changes since langchain-core==1.5.4 release(core): 1.5.5 (#39655) fix(core): make abatch_iterate consistent with batch_iterate for None and zero size (#39367) fix(core): respect pydantic aliases when validating tool inputs (#39572) fix(core): issues in merging chunks (#39535) fi…

    github.com1 month agoView details

  40. codedogQBY/ReadAny

    AI-powered cross-platform e-book reader with semantic search, RAG chat, local vector store, notes, TTS, and WebDAV sync.

    github.com6 months ago34 ptsView details

  41. langchain-ai/langchain langchain-openai==1.5.1

    Changes since langchain-openai==1.5.0 release(openai): 1.5.1 (#39653) fix(openai): preserve streamed encrypted reasoning (#39635) chore(infra): support langsmith gateway in CI (#39651)

    github.com1 month agoView details

  42. radicalbit/radicalbit-ai-gateway

    Radicalbit AI Gateway

    github.com4 months ago18 ptsView details

  43. addyosmani/agent-engineer

    Agent Engineer - a practical course for software engineers

    github.com6 months ago27 ptsView details

  44. shootthesound/Fizgig

    Krea 2, MiniMax & Klein 9B LoRA - LoKR Studio — train, profile, repair, and extract Krea 2, Flux 2 Klein 9B & MiniMax LoRAs & LoKRs

    github.com5 months ago26 ptsView details

  45. ggml-org/llama.cpp b10427

    <details open> sycl: fuse mul_mat(gate) + mul_mat(up) + GLU for q4_K dense FFN (#26779) Measured on Arc Pro B70 (Battlemage, Level Zero), llama-bench -r 20, two interleaved rounds, tg128: qwen2.5-3B-Instruct Q4_K_M 154.18 -> 158.53 t/s +2.8% gemma-2-2b-it Q4_K_M 162.45 -> 165.62…

    github.com1 month agoView details

  46. Netis/heron

    Agent and LLM API performance monitoring via network packet probe. Measures performance of OpenClaw, Claude, Codex, DeepAgents and more — deployed on the provider side, no SDK changes required.

    github.com5 months ago20 ptsView details

  47. ggml-org/llama.cpp b10426

    <details open> ggml: force single thread on wasi (#25686) </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10426/llama-b10426-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64…

    github.com1 month agoView details

  48. ggml-org/llama.cpp b10425

    <details open> sycl: fuse the gated-delta-net state writeback cpy (#26643) Port of https://github.com/ggml-org/llama.cpp/pull/23940. Arc Pro B70, Qwen 3.6 27B Q4_K - Medium (48 of its 64 blocks run gated_delta_net), -ngl 99 -fa 1 -ctk f16 -ctv f16 -b 2048 -ub 2048, interleaved A…

    github.com1 month agoView details

  49. sparkplug604/praxis

    Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

    github.com4 months ago18 ptsView details

  50. anthropics/anthropic-sdk-python v0.122.0

    ## 0.122.0 (2026-08-13) Full Changelog: [v0.121.0...v0.122.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.121.0...v0.122.0) ### Features * **api:** add output_behavior to dream creation (create a new memory store or update the input store in place) ([852c4bb](h…

    github.com1 month agoView details

Newsletter

Get practical AI engineering notes

Receive source-checked analysis of models, agents, evaluation, retrieval, and production reliability. Sent only when there is useful work to share.