New AI tools worth trying, from trending GitHub projects and the brief, newest first.
See the Top 100 this quarter →Memory and passwords stay on-device. 3,200+ stars on GitHub already. If you're building agents that act in real environments instead of simulated ones, it's a cheap way to test that loop this week.
Jobs lazy-load the image and start in seconds instead of minutes, no changes to your job definition. Small plumbing fix, but at world-model training scale, every cut job-start adds up fast.
pairs well with the cleanup above: one agent routing across two Bedrock Knowledge Bases through the AgentCore Gateway, returning cited answers with built-in observability and continuous evaluation baked into the stack.
A short daily scan of launches, open-source projects, and practical workflows.
Haiku routes, Opus plans with extended thinking, Sonnet executes, and AgentCore plus Fargate sandboxes keep generated code from touching anything it shouldn't. A solid blueprint if your "skill" is secretly five agents wearing one coat.
On a Qwen3-4B Portuguese essay grader, cutting unused tokens and fusing common phrases cut real inference cost, runtime and resources together, by 77%, while the bench score went up (0.703 to 0.810).
Open source, Apache-2.0, past 3,200 stars.
Find the cheapest API for any model and connect it from your AI agent: Grandet Skill and an anonymous MCP server, backed by listed prices from 1,800+ official, inference and relay providers on… JavaScript. ★656 on GitHub. Free, open source.
Free, open source.
Heavier than step 3 above, but the blueprint to graduate to once an agent is doing something that matters.
Useful for the diligence-style work Legora is selling, where losing context between sessions is how mistakes slip through.
Spark-x2.5 open model series. Pushing the Limits of Agentic Capabilities in On-Device Models ★823 on GitHub. Free, open source.
An open-source take on ChatGPT's Intelligent UI: answers stream as interactive UI (maps, photos, charts, drawings and working tools). Built with OpenUI. TypeScript. ★702 on GitHub. Free, open source.
Fast CPU OCR: line detection, CTC recognition, reading order, markdown Python. ★606 on GitHub. Free, open source.
A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents TypeScript. ★579 on GitHub. Free, open source.
Looksmaxxing for motion graphics. An agent skill that turns AI slop videos into films that look made by a motion designer. JavaScript. ★749 on GitHub. Free, open source.
A design system for AI applications. Material, physical, tactile, technical. TypeScript. ★930 on GitHub. Free, open source.
Local-first CLI and web dashboard that reads Claude Code, Codex and Gemini CLI session logs and shows token usage and cost by model, project, day and activity. Python. ★700 on GitHub. Free, open source.
Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them. Python. ★777 on GitHub. Free, open source.
A small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a scale faster than an LLM, with a calibrated confidence on every decision. Python. ★570 on GitHub. Free, open source.
Paxeer X is a Distributed HyperState Machine for payments, code execution and intent routing. Designed for Machines and the Users operating them. Rust. ★571 on GitHub. Free, open source.
An agent-first linter. Write your Tailwind design-system rules once, let Claude or Codex verify compliance instead of a human catching drift in review.
Running on Amazon Bedrock AgentCore, their agents now pay each other per inference call over x402, with spending limits enforced at the infra layer instead of the prompt. Worth watching if you're about to let an agent transact on its own.
Shawn Pana's repo lets an agent drive a real Android phone instead of an emulator. Neat demo. Also exactly the kind of access you should be asking "does this agent really need this" about before you wire it in.
Open-source multi-provider AI gateway for Claude Code and other coding agents, with model routing, streaming, tools, reasoning, fallbacks, and local model support Python. ★624 on GitHub. Free, open source.
Distill your knowledge, memories, and decisions into an open-source, inspectable AI Agent Twin. TypeScript. ★585 on GitHub. Free, open source.
Open-source personal finance app with an AI financial advisor: track your net worth, investments, ETFs, cash and debts on your own computer. Python. ★774 on GitHub. Free, open source.
PRINTFILM: AI short-video marketing and AI short-drama creation platform Python. ★4,709 on GitHub. Free, open source.
AWS's pattern for a personal assistant with durable, metadata-tagged memory instead of one blob per user.
A voice travel concierge that reaches the backend only through defined MCP tools, not a standing credential.
AI System Design - Learn how to design AI systems built on LLMs, RAG, and AI Agents step by step. Markdown. ★636 on GitHub. Free, open source.
Spark-x2.5 open model series. Pushing the Limits of Agentic Capabilities in On-Device Models ★660 on GitHub. Free, open source.
AI Chat with powerful models for free PHP. ★1,465 on GitHub. Free, open source.
bounds a chat agent to six typed operations over a deterministic rules engine, so compliance answers ship with a "completeness receipt": compliant plus in-breach plus ambiguous plus unreadable has to equal the number scanned. Same instinct as today's lead: don't let the model grade its own homework.
On ServiceNow's own ITSM benchmark that took Pass@1 from 18.77% to 27.18%. A way to go looking for the state-corrupting cases before a benchmark finds them for you.
A staged code-review workflow and local dashboard built with TypeSafe Jev. TypeScript. ★661 on GitHub. Free, open source.
's ProvenanceGuard is the source for that technique: a post-generation check that keeps each claim tied to a specific source instead of pooling everything into one blob, which is how agents end up citing a real fact from the wrong document.
Amazon S3 Vectors plugs into the NeMo Agent Toolkit as a memory store that scales to 2 billion vectors without you provisioning anything.
colocate multiple agents on one persistent GPU instance with a shared filesystem, instead of spinning up isolated infrastructure per agent. A three-agent music pipeline (compose, master, QA, with the QA agent able to kick work back to composition) ran start to finish in about 400 seconds on a single L4.
swaps weeks of human voting for same-day WER, speed, and speaker-similarity scores across TTS models on the Hub. Useful context: open-weight models make up just 16 of 92 entries on the Artificial Analysis arena it's trying to supplement.
针对GPT 6.0,workbuddyV4.1flash的破甲实验项目 Python. ★835 on GitHub. Free, open source.
AWS's walkthrough post-trains a Qwen3-VL-8B model with GRPO on a Ray cluster, open-source end to end. If you're RL-tuning a vision-language model and dreading the infra glue, this is the reference build.
一个自己找热点、自己写日报的网站框架。把信源和精选标准换成你的，它就是你的行业热点站。 TypeScript. ★2,350 on GitHub. Free, open source.
Nine dotted "thought orb" loading styles for agent UIs, two sizes, auto dark/light, MIT-licensed. Useful if your agent needs a visible "still working" state.
(jub0t) is a free, open-source CapCut replacement that's MCP-capable and cross-platform, 3,765 stars in.
AWS packaged Whisper, wav2vec2 alignment, and diarization into one GPU container you can drop on a real-time or async endpoint for speaker-labeled transcripts.
TypeLLM: LLMs with type-safe generation Python. ★785 on GitHub. Free, open source.
A股行情分析与AI智能投研智能体：股票分析、量化交易分析、盘后复盘桌面工作台——easy stock Go. ★919 on GitHub. Free, open source.
Your Cheat Sheet For AI Engineering Interviews at Top AI Companies - Questions and Answers. Markdown. ★850 on GitHub. Free, open source.
The AI Org-OS — a collaborative platform for humans and agents. Explore: https://spaces.xyne.ai TypeScript. ★734 on GitHub. Free, open source.
CLI for AI-driven test generation and execution from the terminal. The natural check step before a multi-agent diff ships.
Xiaomi's own coding-agent framework, notable mainly because it's a lab, not a startup, betting on agents and models co-evolving.
★709 on GitHub. Free, open source.
Strands Evals now scores whether an agent picked the right skill and actually followed it, not just whether the final answer read fine. Useful if your agent has more than one skill to choose from.
Tokenizers hit v1 with real encode, decode, and scaling benchmarks. Worth a skim before you pick a tokenizer for a new pipeline.
Keep it open for the day step 4 says your local model's fine but your infra isn't.
Open source previs software in the browser: block a scene, pose characters, author camera moves and cuts, then take the same shots to an AI video model. JavaScript. ★714 on GitHub. Free, open source.
Free open-source project designed for turning youtube-viedos into viral short videos. Highlight detection, subtitles, translation, voiceover, all in one for your content. Python. ★750 on GitHub. Free, open source.
if that endpoint is getting called by agent tools, not just apps, check this one. It wires Microsoft Entra ID JWTs through a Bedrock AgentCore Gateway interceptor for per-user, per-tool RBAC/ABAC on MCP tools. Amazon Bedrock AgentCore Gateway is the piece most teams skip until a security review forces it.
(TencentCloud) A self-hosted, multi-user, multi-agent assistant, 4.1k stars on GitHub. Infra economics are the story today (see Nscale's S-1); if you're weighing a hosted agent platform against running your own, this is a credible fork-and-own option.
★971 on GitHub. Free, open source.
AI phone assistant | open-source Python. ★944 on GitHub. Free, open source.
It's the reference implementation for step 1 above.
That's the ephemeral-sandbox half, in production.
Free open-source extractor for AI coding assistant chat histories. Supports Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code, and more. Python. ★839 on GitHub. Free, open source.
Six caching patterns (message content, system prompt, tool defs, mixed TTL, tenant isolation) that cut input token cost up to 90% on repeat context.
Serverless PII redaction with field-level blueprints and a token-matching quality check, built for scanned documents but portable to any transcript with sensitive fields.
(genspark-ai): open-source AI office suite built for this exact handoff, Docs, Sheets, Slides, PDF and Markdown editors plus a CLI so Claude Code, Codex or Cursor can open and edit real .docx/.xlsx/.pptx files on your machine. Bring your own key, no subscription. 6.9k stars.
A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day. Python. ★1,134 on GitHub. Free, open source.
Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views. TypeScript. ★1,960 on GitHub. Free, open source.
Professional agent skills for screenwriting, television writing and dramaturgy Python. ★1,066 on GitHub. Free, open source.
J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research. Python. ★3,009 on GitHub. Free, open source.
If an agent needs to call image generation, this beats wiring the old webui API by hand.
Flatkey media generation CLI for images, videos, audio, text, credits, and model discovery. JavaScript. ★936 on GitHub. Free, open source.
A native control plane for Claude Code, Codex, Cursor, Devin and other coding agents. Rust. ★1,396 on GitHub. Free, open source.
AI Chat with powerful models for free PHP. ★950 on GitHub. Free, open source.
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a… Python. ★994 on GitHub.
MIT, no telemetry, keys stay on your machine.
Free open-source project designed for turning youtube-viedos into viral short videos. Highlight detection, subtitles, translation, voiceover, all in one for your content. Python. ★1,139 on GitHub. Free, open source.
A terminal coding agent that routes across LLM providers by cost, handy if you're already tracking agent spend through the gateway above.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Python. ★911 on GitHub. Free, open source.
3.4k stars. Eight specialist Claude agents behind one coherent persona (FastAPI + Next.js). One config change from being a standing analyst that reads every 8-K for a watchlist.
9.8k stars. Retrieves by rendering documents as screenshots and embedding them with a vision model, so tables and layout survive instead of getting flattened by an HTML parser. Ships with a prebuilt 8.28M-article Wikipedia index and a Claude Code plugin.
A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day. Python. ★854 on GitHub. Free, open source.
Open-source Grok App — desktop workbench (GUI) for the local Grok Build CLI: sessions, projects, media, automations. Tauri 2. TypeScript. ★1,147 on GitHub. Free, open source.
An MCP-linked agent harness that turns a brief into an eight-panel storyboard, handy if you're prototyping agentic creative pipelines instead of gluing tools together by hand.
No tools match this view.