AI page
Repos people are talking about
Ranked by growth inside the window: stars and forks gained, percentage growth, mentions, and how recently the code was pushed. Size alone counts for nothing. Each repo read and explained by AI.
- 41
ZCode is an AI coding workbench from Z.ai that ships as a desktop app, browser-based interface, and terminal agent. The monorepo includes the client, backend services, shared UI, and the source for its Agent CLI and runtime, which can run a TUI or local web UI via a single `zcode` command, with optional SSH/WSL remote workspace support.
Why now: Recently released v3.14.3 and quickly climbing GitHub trending with ~6.8k stars within days of the repo's creation.
- 42
A GitHub repository collecting real AI engineering interview questions from 35 top companies (Anthropic, OpenAI, Google, Meta, NVIDIA, Databricks, Cursor, and more), organized company by company. It also groups questions by topic like LLM internals, inference and GPU performance, RAG, agents, fine-tuning, evaluation, safety, and AI system design, with answers linked where available.
Why now: It recently trended on GitHub as a new, highly-starred repo, reflecting strong demand for AI/LLM engineering roles and interview prep material.
- 43
SemIf is an open-source Python project that lets software make small semantic decisions (routing, retries, yes/no checks) using open LLMs like a 4B Qwen model, reading typed option probabilities directly instead of generating and parsing text. It reproduces the interface pattern of TypeSafe's closed Jev service and runs locally on a consumer GPU, Apple Silicon, or even CPU, with a browser demo.
Why now: It's trending as a popular open-source alternative to TypeSafe's closed Jev service — recently renamed from OpenJev, with active development, a no-waitlist browser demo, and 4.3k stars within a week of creation.
- 44
Laya-MLX is a native Apple Silicon (MLX) runtime for Laya typed decision models: instead of generating text, it returns structured answers (e.g. picking a department from a choice list) for short English questions. It runs fully locally with no PyTorch, Transformers, or cloud API, achieving ~13 ms median latency (7.4 ms multilingual) on an M3 Max, with a pip-installable Python API and a Snake-game demo.
Why now: It's trending among newly starred repos, likely due to the low-latency local typed-decision demos (Snake at 75 moves/s) and benchmark claims versus text-generation approaches.
- 45
A fork of llama.cpp that adds tiered KV-cache memory: completed KV blocks live in host RAM, and a small bounded GPU window is filled with relevant retrieved blocks per step. This lets large-context models like Qwen3.8-27B run at full 256K context on a 16 GiB GPU with near-lossless quality, served via an OpenAI-compatible chat server.
Why now: Recently at the top of trending repos with a new v0.16.0-rc3 prebuilt release, plus benchmark comparisons against KV-cache streaming showing 32-33 tok/s decode on an RTX 5060 Ti.
- 46
NanoJev is a small open-source Python replica of Jev, a 0.6B 'parallel decision' model. Instead of decoding tokens, it takes game states and questions and directly outputs probability distributions over 2–255 candidate choices. The repo includes an end-to-end training pipeline, datasets, and a single checkpoint that plays ViZDoom, Maze, and Snake.
Why now: A recent update (Sept 20, 2026) showed one checkpoint beating the original Jev on ViZDoom benchmarks, with side-by-side browser replays comparing NanoJev, Jev, and untuned Qwen — driving attention on trending repos.
- 47
A curated awesome-list of open-source apps that replace paid SaaS products while running entirely in your own Cloudflare account using Workers, D1, and R2. Entries include Calendly-style booking pages, analytics, feedback boards, inboxes, and more. Each entry is audited: licences are read from licence files and Cloudflare bindings from deploy configs rather than trusting project descriptions.
Why now: It's trending as one of the most starred new repos, riding interest in deploying full apps to Cloudflare's free/cheap tiers instead of paying for SaaS subscriptions or VPS hosting.
- 48
Splash is a local LLM inference engine for Apple silicon Macs, written in C++ with Metal kernels and DFlash 2 speculative decoding. It runs coding agents and OpenAI/Anthropic-compatible apps on one machine, with vision, tool calling, a built-in chat page, prefix caching, automatic memory planning, and optional KV cache offload to SSD.
Why now: It's trending on GitHub's most-starred new repos shortly after release, and its README references a fresh DFlash 2 blog post and an LM Studio integration guide, suggesting recent ecosystem buzz.
- 49
Plexo is a cross-platform desktop download manager (Windows, macOS, Linux) that speeds up file downloads by splitting them into byte-range chunks and downloading them in parallel over multiple network interfaces at once — such as Wi-Fi, Ethernet, USB-tethered phones, or cellular — aggregating their bandwidth into one faster transfer. It auto-detects network interfaces and dynamically scales worker connections per interface.
Why now: It recently appeared among new, most-starred GitHub repos, likely driven by its demo video and the unusual trick of aggregating bandwidth across physically separate internet connections.
- 50
TypeLLM is a Python library that adds type-safe, schema-constrained generation to existing autoregressive LLMs served via SGLang, without modifying model weights. It guarantees outputs like strings, integers, booleans, and enums stay within a JSON Schema, with low token overhead, shared-prefix KV caching, dependency graphs between fields, optional per-field thinking mode, image input, and permutation averaging to reduce option-order bias.
Why now: It's trending on GitHub's most-starred new repos, with rapid daily updates, strong JevBench results (228/231 with thinking), and a recent image-input release.
- 51
A Claude Code plugin and npm library that replaces lossy LLM-based context compaction with verbatim pruning: instead of summarizing old turns, it scores every tool call and result in fast API requests and deletes or truncates only the stale ones. Kept user and assistant text stays verbatim, recent messages are pinned, and it can also be used as a standalone TypeScript package.
Why now: It appeared among the most-starred new repos, likely because it offers a fresh alternative to lossy context-window compaction in Claude Code workflows.
- 52
GoLive is an open-source Agent Skill plus zero-dependency Node CLI that helps you launch apps built by coding agents. It detects what your project needs, proposes a plan, waits for your approval, applies hosting, database, domain, DNS, email and payments setup using your own provider accounts, then verifies results and can tear everything down. No GoLive account, backend or telemetry.
Why now: Trending on GitHub's most-starred new repos, riding interest in agent-driven deployment: it tackles the gap between an agent building an app and actually shipping it, with an approval-first trust model.
- 53
Awesome Jev is a community-maintained, MIT-licensed catalog listing 916 verified open-source projects built with Jev, TypeSafe AI's model for typed decisions in software. Entries are organized into 11 categories (agent tooling, applications, benchmarks, etc.) across 27 languages, with each listing pointing to concrete evidence of how Jev is actually used.
Why now: It's trending as one of the most-starred new repos, actively updated (20 projects added September 25) amid growing ecosystem interest around Jev and Jev-like models.
- 54
Shapeshift is a TypeScript UI component where a single text box dynamically morphs into the right interface as you type — an event card, checklist, timer, color picker, bill splitter, converter, poll, and more. Intent classification is done by the TypeSafe Jev model (or a built-in offline keyword classifier), while dates, amounts, and math are handled by deterministic code.
Why now: It's newly created and rapidly starred on GitHub's trending list, with a live demo and a 60-second video showing the morphing input in action.
- 55
typesafe-computer-use (jev) is a macOS (Windows experimental) computer-use agent that drives your real mouse and keyboard toward a goal typed in plain English. Instead of asking a frontier model at every step, it OCRs the screen and lets a small TypeSafe classifier pick the next action, reserving a writing model only for free text. README claims ~$0.0002 per decision, with facts computed in code, not by the model.
Why now: It's trending as a newly most-starred repo making a bold cost/speed comparison: the README benchmarks its classifier loop against a frontier model (Claude Opus 5) at 130x–390x cheaper and 3.7x faster per step, while candidly noting reasoning must be rebuilt as deterministic code.
- 56
AirCard is a native Windows tool (Rust, ~7.5 MB single executable) that lets iOS 18+ users customize Apple Wallet card faces and apply lockscreen passcode keypad themes without jailbreaking. It detects cards in real time, applies custom artwork over USB or WiFi, and restores the original state afterward using a sync-based exploit.
Why now: It is trending among newly starred repos, likely due to offering no-jailbreak iOS customization on Windows with a lightweight native client.
- 57
A set of Claude Code skills that turn a chess game into a readable post-mortem: it drives Stockfish to analyze every move, generates plain-language explanations, an annotated PGN, an HTML analysis board, and a narrated video. You can also supply think-aloud audio or notes, which the tool transcribes (whisper.cpp) and matches to moves so it critiques your actual reasoning.
Why now: A Show HN post demonstrating the narrated-video output and the novel idea of Claude driving Stockfish to answer human-style 'why' questions
- 58
Von is an open-source, non-autoregressive 'System One' decision model for fast classification, routing, and guardrail-style tasks. Instead of generating text token-by-token, it scores discrete/probabilistic options in a single forward pass, delivering sub-25ms decisions with calibrated uncertainty. Version 1.2 adds order-invariant option scoring, fixing answer flips under option reordering, plus Intel GPU acceleration via OpenVINO.
Why now: A fresh 1.2 release fixing an order-sensitivity defect, demonstrated with a Doom gameplay demo, is drawing attention on the most-starred repos list.
- 59
AnyJev is a Python library that converts any LLM into a calibrated decision model without fine-tuning. It wraps language models to produce typed decisions with real probability distributions (e.g. routing a ticket to billing/technical/sales), fixing order-flip instability and improving calibration. It supports multiple levels, vLLM serving, and fitting a lightweight head with as few as 100-500 labels.
Why now: It recently appeared on GitHub trending as one of the most-starred new repos, with an active vLLM integration making calibrated LLM decision endpoints easy to deploy.
- 60
Rizzo Flow is an open-source, fully local alternative to TypeSafe's hosted Jev service. It turns unstructured state into typed, probabilistic decisions (yes/no, choices, scores) without generating text tokens, using fine-tuned Spark-X2.5 models on llama.cpp. It exposes a Jev-compatible HTTP API, so existing client code only needs its URL changed to localhost.
Why now: Fresh fine-tuned weights (25 Sept 2026) improved accuracy and probability calibration on the typed-decisions benchmark, and it's trending among newly starred repos as a local, open-weights answer to Jev.
- 61
Qwen-Image-2.1 is Alibaba Qwen's newly open-sourced text-to-image generation and editing model. Its 7B-parameter DiT-based visual component generates regular or transparent (RGBA) images, supports editing with up to 10 reference images, local edit regions via masks or annotations, identity preservation, and improved typography and textures, all while staying computationally efficient.
Why now: Freshly released (Sept 20, 2026) with open weights and Day-0 support in Diffusers, ComfyUI, vLLM-Omni, SGLang, and LightX2V; it's trending as a top-starred new repo.
- 62
Bespoke Nimble is an open recipe for building a fast, typed classification model. Given text and a schema of questions (multiple-choice or true/false), Bespoke-Nimble-9B returns each answer with per-choice probabilities in a single step, no chain-of-thought reasoning. The repo covers contrastive data curation, LoRA fine-tuning of Qwen3.5-9B, and serving, runnable on Apple Silicon or NVIDIA GPUs.
Why now: It's trending as a new, highly starred open replication of TypeSafe's Jev System One model, with a recently released 9B checkpoint, public training data, and a shared benchmark suite.
- 63
virtio-nvgpu is an experimental Rust-based virtio device that forwards NVIDIA kernel driver ioctls between a KVM guest and the host at the driver ABI level. The guest runs unmodified NVIDIA user-mode drivers, targeting headless GPU streaming where a compositor in the VM renders and encodes H.264 on the host's GPU. Benchmarks show guest performance within ~2% of bare metal for game-sized frames, with several guests sharing one card.
Why now: It was featured on Hacker News, and it's remarkable because it claims near-native (within 2%) NVIDIA GPU performance in VMs without GPU passthrough — long a pain point for cloud gaming and virtualization.
- 64
Unreal Agent is a Go library for building LLM agents around an async-first architecture. It provides durable, idempotent input handling, append-only forkable session history, tool translators that validate model calls without I/O, and an actor-based operation manager for durable asynchronous work. Components are interface-based and swappable, e.g. proxying operations to remote sandboxes.
Why now: It recently appeared as one of the most-starred new repos, gaining ~2k stars within days of release.
- 65
git-bug is a bug tracker embedded directly in your git repository. Issues are stored as git objects, so you can push and pull them via your normal remotes, work fully offline, and avoid dependence on external services. It offers a CLI, terminal UI, and web UI, plus bridges to sync with other bug trackers and a GraphQL API.
Why now: It was featured on Hacker News, drawing renewed attention to its distributed, offline-first approach to issue tracking.
- 66
Laya-CoreML runs the Laya typed-decision model entirely on-device on Apple Silicon via Core ML and the Neural Engine, returning calibrated probabilities for multiple-choice, score, and boolean questions with no token generation. It includes a local Snake game demo, a Python API, and reproducible latency and energy benchmarks (~5 ms per short decision on M3 Max).
Why now: It's trending as a newly popular repo showcasing validated on-device inference with notable energy-efficiency wins over MLX, though the authors note the claimed 10x speedup was not achieved.
- 67
text-humanizer is a free, open-source Python tool that rewrites AI-generated text to sound more natural and evade AI detectors. It runs a multilingual pipeline: DeepSeek rewrites the text via a Chinese intermediate representation, optional Google Translate and DeepL steps add cross-lingual variation, and a final DeepSeek pass reconstructs fluent text in the original language across 8 supported languages.
Why now: It recently appeared among the most-starred new repositories, gaining attention for openly advertising AI-detector bypass (ZeroGPT and similar), a topic that draws both interest and controversy.
- 68
A demo repo showcasing Claude Opus 5.5's code-generation ability: three playable 3D web games (a pelican biking game, an FPS map recreation, and a drift racing game) each generated from a single one-sentence prompt in one session, with zero human edits to the code. Games are built with Three.js and esbuild into single-file HTML pages deployed on Cloudflare Pages.
Why now: It's trending as a viral one-shot demo of Claude Opus 5.5's capabilities, with playable deployed games serving as proof.
- 69
DeepOpen is an open-source, non-autoregressive 'System 1' decision engine for structured decision tasks like classification, routing, and scoring. Instead of generating text token by token, it produces outputs in a single forward pass, supporting 100+ languages with millisecond-level latency, built on three specialized checkpoints with an automatic router, trained via RLCD reinforcement learning.
Why now: It recently appeared on trending 'most starred new repos' lists and claims strong leaderboard results on the Banking77 and CLINC150 intent-classification benchmarks, with reproducible one-click pipelines.
- 70
A set of Python-based agent 'skills' that offload small, frequent decisions from expensive frontier LLMs to Jev, TypeSafe's decision-only model. It handles model routing, memory filtering, prompt-injection screening, transcript compaction, skill selection, message triage, mailbox sorting, and computer/browser use. Skills ship as plain SKILL.md files, so they work with Hermes agents, Claude Code, Codex, or anything that reads skill files.
Why now: Recently created and climbing the most-starred new repos list, with freshly published evaluation scorecards showing strong injection-detection and recall results.
- 71
InstinctFlash is an open-source C++/Python serving runtime that accelerates robotics model inference. It supports eight model families (VLA, pi05, GR00T, Cosmos, DreamZero, etc.), applies FP8 and sampling optimizations, and reports large speedups over PyTorch on Jetson Thor and consumer RTX 4090/5090 GPUs, with a one-command `serve` entry point for fine-tuned checkpoints.
Why now: Launched via a Show HN post alongside a full-source release and fresh Jetson Thor benchmarks claiming up to 33.78× speedups.
- 72
Dream-RSI is a research project (paper from Google, DeepMind, UMD, UVA) on recursive self-improvement of AI agents. Its key idea is to use accumulated discovery history as a replay simulator so the agent can improve its own exploration strategy, evaluated across 8 tasks in algorithm engineering, math optimization, and GPU kernel engineering, with results like 1.22x faster downstream runtime.
Why now: It's a freshly released preprint (Sep 2026) from Google/DeepMind researchers that quickly gained ~1200 stars, and it claims progress on recursive self-improvement — a hot and controversial topic in AI research.
- 73
Astra Flash Orchestrator is a Python-based Codex workflow that splits AI coding labor by cost: Astra handles planning, architecture, and final review, while the cheaper DeepSeek V4.1 Flash does the bulk implementation, testing, and debugging. It packages work into coherent task bundles, collects evidence, and includes reversible, dry-run installation, with OpenCode support.
Why now: It's trending on GitHub's most-starred new repos, boosted by benchmark claims of ~98% lower cost per 1K lines versus an all-Astra workflow.
- 74
mini-AGI is an experimental byte-level language model that learns continually from a single stream of data without catastrophic forgetting. It trains from scratch on a single 8GB VRAM GPU, stores weights as files on disk and pages them to the GPU as needed, grows new capacity when short, and prunes unused parts. The README notes it's a toy-level experiment, with weights not yet published.
Why now: It was featured on Hacker News as a 'Show HN' post, likely attracting attention because it demonstrates continual learning on modest consumer hardware — a challenge to the assumption that training requires massive resources.
- 75
Neomacs is a work-in-progress hard fork of GNU Emacs that replaces the ~300,000-line C core with Rust and renders the UI on the GPU via wgpu. It aims for 100% Emacs Lisp compatibility, multi-threaded Elisp, 10x performance, and a zero-pause concurrent GC, using GNU Emacs itself as a test oracle to verify identical behavior.
Why now: It was featured on Hacker News as a 'GPU rendered Rust hard fork of Emacs,' sparking discussion about reimplanting Emacs in Rust while preserving compatibility.
- 76
Window Sweaters is a playful macOS menu-bar app that draws knitted-style borders around your windows, like dressing them in tiny sweaters. It offers hand-designed colourways for dozens of popular apps, icon-based colour matching for everything else, and menu-bar controls for styles, border width, and per-app on/off settings. Requires macOS 13+; still a personal work in progress.
Why now: It's a charming, whimsical desktop-customization tool gaining stars on GitHub's trending lists, notable for its quirky concept and the unusual suggestion to install it via a coding agent.
- 77
An open-source Python pipeline that turns long YouTube videos into vertical 9:16 short clips. It downloads the video, transcribes it locally with faster-whisper, uses an LLM (OpenAI, Gemini, or MuAPI) to rank highlights by 'virality' score, dedupes candidates, and auto-crops ready-to-post shorts with subtitles, optional hooks, translation, and voiceover — with no watermarks. Usable via CLI, a local web UI, or an API.
Why now: Trending on GitHub as a most-starred new repo, positioned as a free alternative to paid SaaS tools like OpusClip and Vidyo.ai.
- 78
A Rust command-line tool that queries your local WeChat data: sessions, chat history, contacts, group members, favorites, and stats. It decrypts the local database in real time (no full pre-decryption), caches it via a background daemon for millisecond responses, can export data, and stays fully local. It also exposes agent-friendly output so AI coding assistants like Claude Code or Cursor can call it as a skill.
Why now: It appeared as a fresh, self-described restart of wx-cli and quickly gained ~740 stars on trending lists; also notable that the actual source repo (botiverse/wx-cli) is private, which the README flags as a caveat.
- 79
jevmem is a TypeScript tool that automatically saves decisions, constraints, bugs, and todos from your Claude Code, Cursor, or Codex chats into a JEVMEM.md file, then injects the relevant lines back into context in later sessions. Old decisions are marked superseded rather than deleted, and lines from other sources are checked before recall.
Why now: A v0.5 release just landed, adding Claude Code plugin install, a memory-poisoning check on recalled lines, async background saving, and imports for existing CLAUDE.md/AGENTS.md files; it was also mentioned on Hacker News.
- 80
AgentRun is a JavaScript/TypeScript DSL for defining AI agent workflows as explicit, repeatable steps. Instead of letting an agent improvise, you declare nodes for tool calls, focused decisions (via a 'Jev' judge), and agent invocations, with schemas, deadlines, thresholds, and escalation paths. It ships as an npm interpreter with a TypeScript builder, Zod contracts, parallel mapping, loops, and sub-workflows.
Why now: It was just launched on Hacker News as a Show HN, positioning itself as a structured alternative to free-form agent loops.