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
Tidewater is a browser-based island fishing game running directly on WebGPU/WGSL with a custom-built rendering engine and no framework. You fish from piers, beaches, or a boat, sell your catch, upgrade gear, and explore a tropical island featuring an FFT ocean simulation, physically based atmosphere, volumetric clouds, and wildlife like a breaching humpback whale.
Why now: It's trending as a newly starred repository, notable for being built with 'Opus 5.5' (an AI model) and demonstrating an ambitious custom WebGPU engine with advanced water, sky, and lighting rendering in JavaScript.
- 42
Jev 聊天助手 is an Android 'conversation copilot' that reads the chat currently on your screen (via accessibility services, no app hooking or repackaging), uses LLMs to analyze the other person's intent and draft candidate replies, then fills them into the input box — you decide whether to send. It supports QQ, X DMs, and Feishu (with OCR fallback), and lets you configure your own model APIs.
Why now: It's trending on GitHub's most-starred new repos (~6.7k stars days after its September 2026 release), notable for its non-invasive screen-reading approach and its decision-then-draft pipeline.
- 43
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.
- 44
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.
- 45
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.
- 46
kryvora-node is a Go daemon that connects your machine to Kryvora Network, a decentralized physical infrastructure network (DePIN). The daemon runs a worker engine for task execution, a telemetry daemon that performs probes, and reports proof of availability via mutual TLS heartbeats and verification probes to a central Coordination Hub. Running a node requires an on-chain Genesis Node Key on Arbitrum One.
Why now: It's a brand-new repository trending on GitHub for stars, suggesting recent launch buzz around the Kryvora DePIN network. Note that node operation requires obtaining an on-chain soulbound credential and bootstrap token.
- 47
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.
- 48
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.
- 49
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.
- 50
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.
- 51
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.
- 52
WeChatBridge is a native macOS tool (Swift, sandboxed Share Extension) that adds WeChat's 'forward to other apps' targets so users can send multi-selected chat records—exported by WeChat as a ZIP of text, images, and video—straight to AI agents like Codex, Claude, Doubao, or to Obsidian as Markdown notes, the clipboard, or custom apps. Everything stays local: it reads only WeChat's own exported files, never the WeChat database.
Why now: Recently released a Developer ID signed and notarized 0.1.14 DMG and gaining stars on GitHub trending, riding interest in piping chat context into AI agents.
- 53
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.
- 54
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.
- 55
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.
- 56
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.
- 57
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.
- 58
Foremerge is an open-source coordination protocol for coding agents built on Git. Multiple AI agents working in parallel each declare what they intend to change into a shared SQLite store in your project's .git folder. A deterministic detector flags when two plans collide—like one replacing a class another extends—before any code is written, instead of only catching textual merge conflicts.
Why now: It was featured as a Show HN post ('Catch intent conflicts between parallel coding agents'), tapping into the current wave of multi-agent coding workflows where Git alone can't detect semantic conflicts.
- 59
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.
- 60
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.
- 61
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.
- 62
A TypeScript trading bot that runs an AI model (Jev) against the Kuru MON-USDC order book on Monad, posting a fresh post-only limit order every ~300 ms block to earn the spread rather than pay it. It streams decisions, quotes, fills, gas costs, and PnL to a dashboard via SSE, with a dry-run mode when no private key is set.
Why now: A brand-new, quickly-starred repo (2.4k stars within a day) demoing AI-driven block-by-block market making on Monad, with a live public dry-run dashboard.
- 63
treepeat is a Python CLI tool that detects duplicate and similar code in a codebase using tree-sitter AST analysis plus locality-sensitive hashing. It offers three normalization levels (exact duplicates, near-duplicates ignoring strings/whitespace, and structurally similar code with anonymized identifiers), adjustable similarity thresholds, side-by-side diffs, and SARIF output for CI integration.
Why now: It was featured in a Show HN post, where the author presented it as a proof of concept and invited pull requests to support more languages.
- 64
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.
- 65
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.
- 66
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.
- 67
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.
- 68
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.
- 69
Jevlike is a Python project that trains small models that pick one option from a variable-length list of text options in a single forward pass, instead of generating answers token by token. It independently reproduces the input/output shape of TypeSafe's commercial Jev model, providing training, evaluation, and prediction tools, plus demo checkpoints that score game-controller options (Doom buttons, chess keys) from image patches.
Why now: It's trending on GitHub's most-starred new repos, riding interest in TypeSafe's recently announced 'System One' Jev models whose design was never published, so this open starter implementation fills that gap.
- 70
Jev Review is a TypeScript code-review tool built on TypeSafe Jev. It reviews a Git diff or scans a whole codebase through a staged workflow of typed AI judgments — screening correctness, security, reliability, compatibility, and test coverage — then saves reports viewable in a local, loopback-only dashboard. Findings are meant as review prompts, not definitive defect proofs.
Why now: It's trending on GitHub's new/most-starred repos as an example of composing bounded, typed AI judgments into a practical workflow with orchestration kept in code.
- 71
LocalJev is a local server, written in TypeScript for Bun, that exposes the Jev POST /v1/systemone typed decision API backed by DiffusionGemma through any OpenAI-compatible chat endpoint like oMLX. It converts typed questions into classification prompts, gets JSON probabilities from the model, retries malformed output, and returns Jev-compatible choices, scores, and confidence.
Why now: It just appeared among newly starred repos; the README contrasts it with OpenJev, which needs unmerged vLLM extensions, positioning LocalJev as a portable, wire-compatible alternative — though with self-reported rather than logit-read probabilities.
- 72
Open Glean is an open-source Next.js AI workspace built on Hydra DB, acting as a 'second brain'. You ask questions across your memories, files, and connected apps; it retrieves context, streams answers with inline citations, and offers multi-step Deep Research, collections, mindmaps, integrations, and any OpenAI-compatible model. Keys stay server-side in encrypted cookies, and it can be self-hosted via Docker.
Why now: It appeared among the most-starred new repos, likely drawing attention as an open-source alternative to commercial AI knowledge workspaces like Glean.
- 73
This is the official Git mirror of WordPress core's development repository, synced from WordPress's Subversion. It lets developers fork, clone, run a Docker-based local WordPress dev environment with npm commands, run tests, and contribute patches. Pull requests must reference an existing ticket on WordPress core Trac.
Why now: It was mentioned on Hacker News in connection with a reported unauthenticated path traversal vulnerability in WordPress that can lead to conditional remote code execution.
- 74
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.
- 75
Jev-Code-Reviewer is a local CLI tool plus Chrome extension that reviews GitHub pull requests written by coding agents. It classifies each diff hunk into P0/P1/P2 priorities so humans only see the critical changes by default, shows diffs as natural-language explanations powered by OpenAI, and runs entirely on your machine—nothing is posted to GitHub.
Why now: It was discussed on Hacker News, tapping into the controversy about agents dumping huge PRs (230-file changes) that humans 'YOLO merge' without real review.
- 76
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.
- 77
A local Go-based tool with a web panel that tries to improve Codex's connectivity, rate-limiting, and quality-degradation issues. It captures and injects the X-Codex-Turn-State header via proxy exits, supports Astra/Sol/Terra models, official ChatGPT login, API keys, and relay providers, with proxy/subscription management and diagnostics.
Why now: Recently created and gaining stars quickly; Codex users are actively discussing perceived 'degraded' model quality and rate limits, and this packages community workarounds into a usable one-click tool amid caveats that no specific state or quality gain is guaranteed.
- 78
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.
- 79
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.
- 80
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.