Havuz

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.

Spark-X2.5, yerel çalıştırma ve agent iş akışları için tasarlanmış 1.7B ve 4B boyutlarında açık dil modelleri serisidir.

Neden yükseliyor · Yeni model serisi; uzun context, küçük model boyutu ve agent/coding yeteneklerini aynı anda öne çıkarıyor. README'de 34 günlük yaş, 386 yıldız ve son 28 günde 9 commit ile 2 farklı yazar bilgisi var; bunlar erken ilgi ve güncel çalışma gösteriyor, ancak model performansını bağımsız olarak kanıtlamıyor.

SkillClaw, AI agent’ların oturumlar boyunca edindiği deneyimlerden skill’leri arka planda güncelleyip birden fazla agent arasında paylaşmayı hedefleyen Python yazılımıdır.

Neden yükseliyor · 171 günde 2643 yıldız dikkat çekici bir ilgiye işaret ediyor. Agent skill’lerini otomatik geliştirme ve birden çok agent arasında paylaşma fikri güncel bir ihtiyaca yanıt veriyor; ancak son 28 günde commit ve farklı yazar sayısı sıfır. Bu nedenle ilgi, sürdürülen geliştirme veya benimsenme kanıtı olarak tek başına yeterli değil.

Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.

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

Design workspace for programmable 3D. Nova builds assets and worlds as editable, versioned programs: parametric, articulated and simulation-

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, C

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

Tactical AI Workspace Monitor & EDR

Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Studio, MLX, llama.cpp) or cloud,

Transformer architecture explained step by step - the full architecture, every attention variant, positional embeddings, and every layer ins

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and

AI-powered dating simulator

Forge is an open-source, self-hosted alternative for visually building and shipping AI agents and workflows without giving up control of you

Handling 10M+ docs using RAG with zero hallucinatons

A local-first AI workspace : multi provider chat, a Full Harness in Hashcoder agent, 3D models, ERPs, and multi-agent swarms in one native d

llama.cpp fork that abliterates at inference

Custom tools to enhance your Open-Webui Experience! 🚀

Local-first YOLO workbench for annotation, training, evaluation, and AI assistance.

An open-source text language, parser, validator and Three.js renderer for inspectable 3D human movement.

Evaluation Metrics for African Languages

Use OpenCode Zen's free models in any coding agent. OpenAI + Anthropic compatible, so Claude Code works too. No account, no API key.

Agent Deck

AI-powered multi-agent security auditor for Symfony applications, provider-agnostic via symfony/ai.

An end-to-end framework for Agentic Reinforcement Learning.

Complete Production Environment for professional MiniMax Music 3 audio generation, including Prompt Generation, Metadata generation includin

The official FastMCP TypeScript library for building MCP servers, clients, and apps 🏎️ 🏎️ 🏎️

Token efficient IDs for AI agents. UUID alternative for the agentic era.

PortableLM — Zero-dependency, air-gapped local AI that runs entirely from a USB drive. Chat, generate images, and synthesize speech offline

Take the 100 Days of AI challenge - learn one AI concept a day, from machine learning basics to AI agents in production, in 100 days.

[ACL'26 Main] Official code for "LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning".

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.

Multi-Provider AI Gateway - No personal logs by design. Model autodiscovery, Failover groups, High availability, Android companion app, and

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.

The DeepSeek and OpenRouter Harness built on Elixir

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

Sandboxed OCI container images for AI coding agents, built reproducibly with Nix.

Autonomous trading agents with deterministic execution. The agents propose; the system decides.

Self-hosted, distributed, multi-model LLM inference

核弹，椅子，瘫坐！DSH新预设模式“工程模式”，只需要你说出“请帮我完成一个机械臂”，你的AI模型靠内部的工作流，按照要求完成对应机械的设计，完全实现“AI设计机械，无需人工干预”的场景！(测试版本：SW ：2025 DSH:0.2.1 rc3 ）

An LLM-powered social simulation and roleplaying engine where NPCs have their own lives too.

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

Free, Privacy first open-source manga translator. Run everything locally on your GPU, use Gemini, or connect your own LLM. Bubble detection

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

Discovery Foundation Models (DFMs)

A complete, hands-on journey from Python fundamentals to AI Engineering. Explore Data Analytics, Data Science, Machine Learning, Deep Learni

🤖 A minimal agentic loop for building efficient harnesses.