Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and how that access is handed off.
☆291Nov 8, 2026Updated this week
Alternatives and similar repositories for berth
Users that are interested in berth are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, …☆74Nov 4, 2026Updated last week
- Qwen3.8-Flash-Next (MoE) and Qwen3.8-27B on one or two 16 GB RTX 50-series GPUs: experts offloaded to CPU, two-GPU tensor parallel. 64 GB…☆140Updated this week
- Interactive desktop app with 58 labs covering ML fundamentals, transformers, RAG, agents, fine-tuning and quantization and more.☆252Oct 31, 2026Updated last week
- Bounded rolling context and exact history recovery for Pi☆35Oct 31, 2026Updated last week
- Local, full Windows search replacement, clipboard manager, and launcher: files, apps, settings and semantic media search with Google's Em…☆43Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Qwen3.8-Flash-Next (125B MoE) up to 1M context on one or two RTX cards (tuned on 3080 10gb). A measured, tuned and benchmarked fork of …☆57Updated this week
- Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s on agent tasks, ~4…☆503Updated this week
- Fast, lightweight and stealth Firecrawl alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Fir…☆79Oct 18, 2026Updated 3 weeks ago
- ☆32Oct 23, 2026Updated 2 weeks ago
- GamePause for Local AI: a Windows tray app that pauses LM Studio, Ollama and other local AI servers while you game, and restores them aft…☆25Oct 18, 2026Updated 3 weeks ago
- Qwen3.8-Flash-Next at full 262k context on 8 GB RAM and 16 GB VRAM—20 tok/s generation and 1,600 tok/s prefill.☆66Oct 26, 2026Updated 2 weeks ago
- Review boards for UI mockups, as a Hermes plugin: mark decisions, pin comments, press Send, and your agent wakes up with the feedback.☆23Updated this week
- Local-first AI workflow orchestration for chaining models, agents, tools, and scripts into repeatable workflows.☆33Aug 10, 2026Updated 3 months ago
- An AI workforce on your desktop. Describe the work; a team of AI agents does it in the open and hands it back checked. Any model, any har…☆44Oct 22, 2026Updated 2 weeks ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- What's your LLM's personality? Measure warmth, patience, confidence and 5 more axes from hidden states.☆14Jul 29, 2026Updated 3 months ago
- Local inference engine for Qwen3.8-Flash-Next on NVIDIA Blackwell☆869Updated this week
- A workbench for language model research☆111Aug 9, 2026Updated 3 months ago
- monitor for a local LLM runtime (llama-swap, NInfer, Strata, more) -- metrics ported to berth.☆13Oct 17, 2026Updated 3 weeks ago
- Open-source control panel for the real llama.cpp: see where a model lands in your VRAM before loading, every llama-server flag per model,…☆122Updated this week
- A friendly Linux UI for local AI: chat, agent, models, backends, all in one☆20Updated this week
- Real-world percentile benchmark for LLM inference servers: 1% A/B resolution, offline HTML reports. I am now on X also: https://x.com/bku…☆83Oct 9, 2026Updated last month
- Memory system for LLMs that remembers everything you teach it during conversation. No reindexing, no context window limits. CPU by defaul…☆13May 2, 2026Updated 6 months ago
- Chain two LLMs — local or cloud: a Prompter that refines your idea, and a Coder that writes the code.☆33Jul 18, 2026Updated 3 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ to…☆310Updated this week
- Multi-dataset evaluation of Anthropic's J-Space on Qwen3-4B. Demonstrates that internal 'workspace noise' can reliably route high-confide…☆12Jul 13, 2026Updated 3 months ago
- An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ RTX 30/40/50-series cards Qw…☆140Updated this week
- ComfyUI workflow for realistic iPhone-style influencer photos (Kromoss) + pose/expression edit (Qwen Image 2.1 BFS), with an installer fo…☆33Oct 25, 2026Updated 2 weeks ago
- Process all your context faster with LLMs that can skim and selectively read what matters☆115Updated this week
- A easy ui to quickly trim down small segments of a larger video and bulk run them.☆21Aug 14, 2026Updated 2 months ago
- Real-time, low-latency audio streaming from your Windows PC to an Android device.☆21Oct 22, 2026Updated 2 weeks ago
- Deterministic spec-orchestration for local LLMs in the pi coding agent — drives prompts through refine→research→grill→compose→critique, w…☆148Oct 24, 2026Updated 2 weeks ago
- 🤖 A minimal agentic loop for building efficient harnesses.☆28Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Plugin for Guitar Hero III (PC / BetterGH3 / GH3+) to report gameplay state over MQTT in order to trigger Home Assistant automations. e.g…☆12Oct 24, 2026Updated 2 weeks ago
- Self-hosted MCP server for image generation and editing with the uncensored Qwen-Image-2.1 model☆117Oct 11, 2026Updated last month
- You type. It already knows. Local LLMs that read and think while you type.☆80Updated this week
- ☆17Oct 30, 2026Updated last week
- OwlLayer AI - Open-source TypeScript Agentic UI SDK for AI-powered interfaces across React, Vue, Angular, Svelte, Vanilla JS/HTML and PHP…☆18Oct 11, 2026Updated last month
- Turn your agent into a mentor. It knows what you're working toward, and how you get in your own way.☆17Aug 7, 2026Updated 3 months ago
- handwritten harness for AI, not vibecoded, everything is a module/plugin, tailor made for use with local models, tiny system prompt (arou…☆534Updated this week
Are these results useful?