精选 AI 原生公司 · 不含传统科技巨头
自动从 Product Hunt、HN Show HN 收录 · 质量参差不齐，仅供参考
a free, open-source multitrack audio editor for the web
a better GitHub. Open-source, anti-AI, and written in Rust
open-source UI kit for modern document apps
Continue? Y/N: A 60-second game about AI agent permission fatigue
Roll your own Claude in 100 lines
A Claude Code statusline that shows live World Cup scores
free extension to protect AI agents on the web
A zero-token audit log to catch rogue Claude Code subagents
AgentKitten: Swift package for provider-agnostic AI agents
coordinate LLM agents by service boundary, not role
AI Pair Programmer for Emacs
AISlop, a CLI for catching AI generated code smells
An LLM translator whose source is a single prompt
AI code reviews grounded in 12 classic engineering books
Collaborative Claude Code sessions, stored in Git branches
Open-source fingerprint-hardened Browser for Scraping
Claude Code's $200 plan is a 17× subsidy on the raw API
forecasting Claude Code usage limits with a Gamma process
An Open-Source, Unix-like, biomimetic, flat-file AI Harness
a Pi and self-hosted research harness on low-budget GPU
an embedding-model upgrade should be a rotation, not a reindex
open-source WYSIWYG Markdown editor for the terminal
why our browser agent writes JavaScript not CLI commands
an open-source web-based file manager
a Go LLM agent framework with built-in tracing and replay
I applied Lyapunov stability theory to detect when LLM agents spiral
I built a tool to auto-accept AI slop and bigtech devs loves it
chat and voice, MIT
I run a vision model on every screenshot, locally, on a 4GB GPU
AI-native language to catch prompt injection at compile-time
Open-source legal AI that abstains instead of hallucinating
A read-only Kubernetes context engine for SREs and AI Agents
a context aware CLI coding agent built by coding agents
Open-source executable context layer for data agents
Learn from 30 historical figures, open source, nonprofit, self-hosted
Lich, start a dev stack per coding agent in parallel
Self-Hosted Cursor Agents — Use Claude Code/OpenCode
Python library for cache-optimized LLM conversation history
Local Coding Agent with LLMs to Delegate Tool Calls to Small AI Models
Local note engine uses LLM to organize notes into a knowledge graph
Loom, an open-source delivery harness for coding agents
pluggable CLI filter that saved 91.8% of my LLM tokens
macOS menu bar gauges for your Claude Code quota
Magenta Real-Time Music Generation on iPhone, Without the GPU
local-first AI memory layer for any LLM — Rust, SQLite,petgraph
self hosted runtime for AI agents
Nightwatch, The open-source, read-only AI SRE
Open-source API Key server written in Go by Ory
end-to-end encryption
OpenClaw and Hermes Agent call each other via XMPP
open-source guts for a 1996 coin payphone — Pi and SIP
OpenSkynet Your AI Terminator
OpenYabby, voice-controlled multi-agent orchestrator for Claude Code
Lightweight Jira alternative for human-AI collaboration
Beautiful open-source coding agent interface
Patina, an AI that learns your judgment, not just your tasks
data contracts, migration graphs, agent DX
Remuda, a CLI Agent Orchestrator
600-line Python
Script to bulk delete Claude chats from the web UI
The zot coding agent, one click away on macOS
Skill for your agent to visualize your gbrain and Obsidian
171 structured reasoning skills for Claude Code
Sub-Agent MCP: LLM delegation and sub-agent orchestration via MCP
the open-source company brain behind my YC startup
<500ms stateful rollbacks for AI agents via CRIU
high performance LLM inference engine in C++ and CUDA
Tired of duct-taping access control into agent prompts. Here's the fix
executable behavior specs for AI coding agents
Package and import portable AI coding-agent Harnesses
Viveka: filter LLM output against a Lean-verified Advaita Vedanta model
open-source terminal coding agent in Rust
Waiting for AI Grand Prix racing SIM? Me too So I made one
Command Center, the AI coding env for people who care about quality
Generate Claude Code Workflows using Spec Driven Development approach
I built a powerful RAG and knowledge graph agent that runs locally
I built a RAG and knowledge graph agent that runs locally
Lessons learned from running Claude Code swarms at scale
An AI-friendly markup language for PDF generation
Spec-Driven Development Workflow for Claude Code
#1 on olmOCR-Bench
an OOXML-compatible AI presentation maker
Rayline routes Claude Code subagents to on-device and cheaper models
The agent that builds and operates its own SaaS tools
A Highly Available Distributed Router for Global Realtime AI
I put my Claude Code rate-limit burndown in the status line
Generated with Claude Fable 5
Local-First Question-to-SQL-to-Dashboard AI
A shared web-map registry for AI agents — MCP, open source
LLM proxy for coding agent context and memory management
Sandbox AI-app lifecycle, from build to run
A better LLM-wiki with multi-path research [550 stars]
Why you can't do data analysis with Claude
open-source canvas IDE for agentic coding workflows
I had Fable clone a game, it turned it into an arena combat AI trainer
An AI that tells you your business idea isn't good
run AlphaEvolve on your Claude Code/Codex for dirt cheap
RiskKernel, kill -9 an AI agent and resume it without paying twice
A 150M model that extracts verbatim evidence spans for RAG, no LLM call
AI Videos, Self-Hosted Nvidia Cosmos on H200 GPUs