Havuz

NeveAI é uma plataforma de IA local privacy-first, desenvolvida para oferecer uma experiência de alta performance na execução de LLMs, reduz

Big models. Small Macs. Zero excuses.

Six Claude Code skills that harden Opus 4.8 toward frontier behavior. Written by Fable 5, pressure-tested on the target model with transcrip

AI travel planning engine with deterministic route scheduling, verified POIs, and fact-grounded LLM generation.

Defense-in-depth security toolkit for LLM agents — taint tracking, proxy secret guard, policy engine, and red-team benchmarking

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)

Chain two LLMs — local or cloud: a Prompter that refines your idea, and a Coder that writes the code.

Jump Skill Ninjas are intelligent meta-skills — master orchestrators that route your requests to the most appropriate specialized skill from

🤖 A minimal agentic loop for building efficient harnesses.

Widen is a free, open-source, native macOS Postgres GUI. Its agents use open-source LLMs based on DeepSeek and hosted in the US

framework for using llms on object grounding

Aprendendo como agentes de IA funcionam de verdade.

An open standard for push-based, verifiable communication between digital entities and agents that follow them.

OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models

Local-first desktop coding agent with BYOK, MCP, and OpenAI-compatible / Ollama hosts

Unified interface to call OpenAI and Anthropic compatible LLM APIs from Rust and other languages

A complete, structured end-to-end roadmap to become a versatile Generalist AI Engineer from Python/math foundations through ML/DL, CV, NLP,

Deterministic cost / loop / time budgets · full observability · crash-resumable runs · human-approval gates · a memory you own. Self-hosted.

10 skills that cut your AI bill with proof instead of vibes. MIT, works in Claude Code, Codex, Cursor. Every skill's check is executed by CI

Embedded code reviews directly directly within pi.

Making MoE fine-tuning accessible to anyone with consumer hardware.

Use LLM judgment in regular Elixir control flow.

A Windows tray dashboard for Claude Code, Codex, Gemini, and Grok usage limits.

A high-performance, private, on-device AI chat client built with Flutter. AstraLM runs Large Language Models (LLMs) and Vision models 100% l

Reverse T9 for LLMs. Free, open-source prompt compressor for your AI prompts and agents.

Logic programming for AI agents: Datalog-family language compiling to optimized SQL

The most complete and flexible Astro integration for LLMs and generating markdown versions of pages. Per-page .md siblings, llms.txt index,

Structured output generation for LLMs in Node.js — token-level constraints for local models, native JSON modes for cloud APIs

Context-aware technical term explanations for Chrome and Edge, powered by Rust/WASM and optional LLMs.

Zero-infrastructure, local-first memory for AI agents. One SQLite file — no Postgres, Neo4j, or cloud. Bi-temporal supersession (updates, ne

One-stop AI toolkit for building, integrating, and scaling AI-powered products with JPMorgan Payments APIs.

📱⚡ Autonomous, zero-VoIP AI voice calling system bridging Android SIM cards directly to Google Gemini LLM & Microsoft Edge Neural TTS over A

An arena where LLMs write robot controllers and their code competes.

A highly customizable shadcn registry template repository built with TanStack Start. Fork, customize, and deploy free to Cloudflare Workers.

Self-healing infrastructure for AI agent payments. 90.3% auto-recovery.

Paritok, coding agent isteklerini LLM'e iletmeden önce sıkıştıran ve sıkıştırılmış içeriğin gerektiğinde geri alınmasını sağlayan bir gateway'dir.

Neden yükseliyor · Token maliyeti ve context window kullanımı coding agent ekipleri için görünür sorunlar; drop-in entegrasyon vaadi anlaşılır bir değer önerisi sunuyor. 74 günlük repo için 1.453 yıldız ve son 28 günde 12 commit, 4 farklı yazar ilgi ve yakın dönem aktivitesine işaret ediyor; bunlar tek başına ürün kalitesini kanıtlamıyor.

[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluatio