Run Hy3 on a 10GB-RAM consumer machine β pure C, zero deps, experts streamed from disk. Tiny engine, immense model. π¦
β71Aug 3, 2026Updated 3 months ago
Alternatives and similar repositories for colibri-hy3
Users that are interested in colibri-hy3 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- peng - colibri-style streaming MoE engine for MiMo-V2.5 (311B) on consumer hardwareβ26Sep 6, 2026Updated 2 months ago
- A full, unpruned 177B MoE model at 11.5 tok/s on one 12 GB GPU. Expert streaming for llama.cpp, with the measurement harness and every deβ¦β25Oct 3, 2026Updated last month
- A friendly Linux UI for local AI: chat, agent, models, backends, all in oneβ20Updated this week
- Multi-dataset evaluation of Anthropic's J-Space on Qwen3-4B. Demonstrates that internal 'workspace noise' can reliably route high-confideβ¦β12Jul 13, 2026Updated 3 months ago
- You have the vision. Put an AI workforce behind it. Your AI Chief of Staff and a team of specialist agents, on Mac, Windows and Linux.β18Updated this week
- Wordpress hosting with auto-scaling - Free Trial Offer β’ AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Giant MoE models on a single consumer GPU by streaming experts from SSD. CUDA fork of antirez/ds4: runs GLM-5.2 (743B), Tencent Hy3 (295Bβ¦β40Jul 12, 2026Updated 3 months ago
- Multi-model AI consensus loop via CLIβ19Jul 1, 2026Updated 4 months ago
- β21Jul 4, 2025Updated last year
- Web based coding and computer use agent. Multi session. Voice chat. Browser use.β23Updated this week
- Create 2D fluid simulations based on metaballs - example of fluid simulation in Defoldβ11Jul 22, 2020Updated 6 years ago
- Command Code mod: nudges the agent to keep going when it stops with work left, judged by Jevβ22Sep 22, 2026Updated last month
- Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploysβ¦β30Updated this week
- Practical MiniMax-H3 prompt validation, canvas planning, audio reroll, and AV latent tools for ComfyUI.β11Aug 4, 2026Updated 3 months ago
- Antigravity CLI integration for Claude Code and Codex.β19Oct 16, 2026Updated 3 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer β’ AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Convert any workflow into an easy-to-use WebApp interface without enabling Node2.0 / ε°δ»»ζε·₯δ½ζ΅θ½¬ζ’δΈΊζ΄ζδΊδ½Ώη¨η WebApp ηι’δΈζ ιε―η¨ Node2.0β16Aug 15, 2026Updated 2 months ago
- The game engine built for AI agents. Games are JSON, errors come with fixes, and agents play-test their own games headlessly.β21Updated this week
- Nodes for generating seamless tiles with any modelβ14Jul 14, 2026Updated 3 months ago
- Lightweight self-hosted chat interface for OpenAI-compatible APIs and local models.β33Oct 22, 2026Updated 2 weeks ago
- β13Apr 28, 2026Updated 6 months ago
- Frontier MoE models on RTX PRO 6000 / RTX 5090 (sm_120): DeepSeek-V4.1-Flash on 4x RTX PRO 6000, as a GPU+CPU hybrid on 4x RTX 5090, and β¦β569Updated this week
- Local-first AI workflow orchestration for chaining models, agents, tools, and scripts into repeatable workflows.β33Aug 10, 2026Updated 2 months ago
- β12Jul 16, 2026Updated 3 months ago
- A local-first web search agentβ29Jun 20, 2026Updated 4 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer β’ AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ComfyUI custom nodes for NVIDIA Cosmos3-Nano (text/image-to-video + audio)β15Jul 28, 2026Updated 3 months ago
- The most extensive public dataset of historical painters on the internet. Created from combining WikiArt and Art500k painting data, enricβ¦β16Nov 7, 2025Updated last year
- Builds manifest file used by DLSS Swapperβ34Oct 14, 2026Updated 3 weeks ago
- Gives agents a real browser. URL in, pruned snapshot out. Replaces Playwright, Selenium, Puppeteer. Zero deps, zero wasted tokens.β46Oct 30, 2026Updated last week
- GPUDirect Storage (GDS) for the NVIDIA CMP 170HX on modern Linux kernels (6.18+). nvidia-fs NVMe registration hooks for the new blk_rq_dmβ¦β18Aug 19, 2026Updated 2 months ago
- WebUI for managing llama-server sessionsβ31Nov 1, 2026Updated last week
- β10Oct 8, 2026Updated last month
- An AI-powered agent system generating and verifying Lean 4 code, translating natural language problems into formally proven programs usinβ¦β22May 30, 2025Updated last year
- Patch kit for making oh-my-opencode-slim and superpowers cooperate cleanly in OpenCodeβ14Jul 15, 2026Updated 3 months ago
- Proton VPN Special Offer - Get 70% off β’ AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- agents container docker in dockerβ19Oct 24, 2026Updated 2 weeks ago
- Juego de estrategia en tiempo real en Three.js, de 1800 a 2100. Todo procedural: cero assets binarios.β22Aug 1, 2026Updated 3 months ago
- High-performance batched Top-K selection for CPU inference. Up to 80x faster than PyTorch, optimized for LLM sampling with AVX2 SIMD.β18Mar 20, 2026Updated 7 months ago
- β13Aug 2, 2026Updated 3 months ago
- Turn a Windows 11 IoT LTSC PC into a couch gaming console: boots straight into Steam Big Picture, survives crashes, desktop only on demanβ¦β21Aug 24, 2026Updated 2 months ago
- Interpost AI Internal Links (formally "Contextual Link Weaver") is an intelligent internal linking assistant for WordPress that uses the β¦β14Sep 3, 2026Updated 2 months ago
- Echo Mode β A semantic resonance protocol for LLM tone controlβ13Oct 7, 2025Updated last year