mistatic

A minimal self-hosting platform that publishes HTML or ZIP uploads immediately

An on-demand self-hosting tool for developers who want to deploy static sites for demos, tests, or AI proofs of concept by uploading an index.html or ZIP file for immediate serving.

oto-dock

A Claude- and Codex-based AI agent platform for teams to run on their own servers

Organizations can create role-based AI agents, share them across departments, and run them on schedules or in response to webhooks. They can use each user's subscriptions and local models, and continue work between the server and personal computers.

Stroq

Scans what the agent reads, taints the session, blocks the dangerous follow-up — before anything leaves your machine.

holaOS

Open-source agentic workspace enterprises can make their own.

Spnda

Zero-cost epistemic uncertainty quantification & hallucination detection for LLMs (90,000x faster than Semantic Entropy) - Adarshent/Spnda

fafo

A coding agent tutor for learning evaluations by examining failures, fixing graders, and practicing

A hands-on repository for developers who want to learn by working directly with AI evaluations. Its included skill guides them through analyzing failures, fixing faulty graders, and experimenting with their own cases, asking them to predict results before seeing the answers.

pixel-agents

A pixel-art mission control for your Claude Code agents — every project is an office, every agent is a character - mateovalle/pixel-agents

MaruCheck

Independent QA and verification for AI-generated software.

egma

Test voice agents with simulations and monitor them in operation.

A platform for teams developing and operating voice agents to test their behavior through simulations and monitor them after deployment. It supports LiveKit and Retell integrations and self-hosting.

kern-ai

Agents that do the work and show it.

huggingface

A small language model built to train and run Korean character chatbots on personal hardware.

A Korean-only model with 254.7M parameters, built so developers and students who want to create character chatbots can experiment repeatedly with limited resources. The desired personality and speaking style must be fine-tuned using example data.

BiNeuron

BiNeuron is a local AI assistant that detects programming languages from requests/files, selects specialized models based on hardware, and generates code/docs/analysis v…

symphony

The live map of your AI coding agents.

ridge-core

A resource mesh that lets agents handle multiple compute and storage resources consistently

Connects local projects, Docker, SSH machines, and S3 storage through a common interface so AI agents can discover and use them, while coordinating access permissions and results across multiple agents.

ctrlb-decompose

LLM-ready reasoning surface over logs.

emailclaw

The Ultimate AI Agent for Email Lovers!

linubot

Your own team of AI helpers in a Linux desktop app.

inversql

A tool that uses decision trees to generate SQL matching selected records.

Users who find it difficult to express the desired result directly in SQL can select records to generate matching SQL candidates. It uses decision trees and displays the shortest candidate on screen.

engrim

The Universal Cross-Model Episodic Memory Standard.

injoffice

A collection of open-source libraries for adding document, sheet, slide, and PDF editing to apps.

Developers building office file editing features can handle files with TypeScript and Go components for browsers and servers, connecting a local WASM engine or their own backend as needed.

Korean-llm-v4

A 1.09B-parameter LLM built from scratch for Korean pretraining and SFT — supports RoPE, KV Cache, BF16·8-bit AdamW optimization, dataset caching, and training monitoring.