Best AI products · September 2026

Discover the AI products launched Sep 1 – Sep 30 UTC. Live, votes are still coming in.

←

Ranked by votes, comments, and recency41 launches

🥇
Vorlagenplatz✨ Featured
Vorlagenplatz bietet kostenlose Vorlagen zum direkten Ausfül
Kostenlose Vorlagen zum Ausfüllen & Ausdrucken Fülle Vorlagen direkt online aus oder lade die leere Version als PDF herunter – ohne Anmeldung und komplett gratis. Von der Kündigung bis zur Bastelvorlage. Vorlage suchen
💬 0Research & DataDesignFreeby Kashif Nazir Khan
2
Mini-AGI
Dynamic continual learning model trained on 8GB VRAM
Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of data. - volotat/mini-AGI First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49783133
💬 0Y▲ 277 on HNLLMs & InfrastructureFreeby AI Launch Team
3
Cactus Needle 3
8-29MB automation models can match DeepSeek V4 Flash
A foundation model for mobile, wearables, robots, smart home, automotive and microcontrollers. One 8-29 MB binary that beats models 10x its size on mobile tool calls and matches 2-3x bigger models on extraction. First shared by its maker o
💬 0Y▲ 236 on HNLLMs & InfrastructureProductivityFreeby AI Launch Team
4
LLM Attention Visualization
A visualization of the attention mechanism in LLMs.
A visualization of the attention mechanism in LLMs. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49613068
💬 0Y▲ 177 on HNLLMs & InfrastructureFreeby AI Launch Team
5
JevBench
A reproducible benchmark for typed decision models
Compare Jev-class decision models across intelligence, calibration, speed, and cost with JevBench. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49800574
💬 0Y▲ 153 on HNLLMs & InfrastructureFreeby AI Launch Team
6
Kinesis
Control your Mac with the Meta Neural Band
native macos controls for the meta neural band (highly experimental) - callbacked/kinesis First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49695408
💬 0Y▲ 122 on HNProductivityFreeby AI Launch Team
7
TinyAIArena watch AI agents battle it out
Tiny AI Arena
First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49867775
💬 0Y▲ 120 on HNAI AgentsFreeby AI Launch Team
8
A competition for small neural networks that play strategy…
build the smallest brain that plays well
A ranked ladder for small neural networks that play strategy games. Train a model, write an adapter, upload two files, and get measured into a weight class from 8 KiB up. First shared by its maker on Show HN: https://news.ycombinator.com/i
💬 0Y▲ 116 on HNProductivityFreeby AI Launch Team
9
CUA-S1
A System One Model for Computer Use
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation. - trycua/cua First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49767564
💬 0Y▲ 95 on HNLLMs & InfrastructureFreeby AI Launch Team
10
Pac-Bench
How well can models one-shot a Pac-Man game?
PacBench: how well a model and harness can recreate Pac-Man from a single prompt. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49885493
💬 0Y▲ 78 on HNLLMs & InfrastructureFreeby AI Launch Team
11
A Claude Code skill to analyze your chess games
Stockfish-backed annotated PGN, HTML viewer, narrated video
Claude Code skills for chess post-mortems: Stockfish-backed annotated PGN, HTML viewer, narrated video - brumar/chess-postmortem-skills First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49857528
💬 0Y▲ 75 on HNCoding & Dev ToolsFreeby AI Launch Team
12
Lossless-memory
A personal AI memory that never summarizes
Lossless long-term memory for a personal AI: never summarize, keep every line, put a timestamp on everything. - aru-labs/lossless-memory First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49786419
💬 0Y▲ 67 on HNProductivityFreeby AI Launch Team
13
Jevstiller
Distill Jev into a local model – with a disagreement bound
September 2026. Every number here is from the benchmarks, and bash experiments/bench.sh --no-record reruns them without an API key. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49891769
💬 0Y▲ 63 on HNLLMs & InfrastructureFreeby AI Launch Team
14
Pizza Bot
An inbox for AI agents that work in the background
A local-first inbox for long-running AI agents, built with DeepAgents and LangGraph. - pizza-bot-app/pizza-bot First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49713894
💬 0Y▲ 61 on HNAI AgentsChatbots & AssistantsFreeby AI Launch Team
15
MultiMatte
A Promptable Image Background Removal Model
MultiMatte is a promptable image background removal model. Tell it what you want to keep, and MultiMatte will remove the rest. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49645803
💬 0Y▲ 57 on HNLLMs & InfrastructureImage GenerationFreeby AI Launch Team
16
Ordewell
Turn one goal into an ordered plan of coding-agent tasks
Multi-agent task orchestration for coding agents. Turn one goal into an ordered plan of tasks (each with its own runner, model and mode), then execute and verify the results. - ordewell/ordewell First shared by its maker on Show HN: https:
💬 0Y▲ 56 on HNAI AgentsCoding & Dev ToolsFreeby AI Launch Team
17
Doom or Bloom
Map your AI worldview
Map your AI worldview, and compare it with others. Explore how public figures think AI will change our future, then discover where you land. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49846953
💬 0Y▲ 56 on HNProductivityFreeby AI Launch Team
18
Self-hosted company OS
Claude Code and Codex agents in departments
The agentic company OS. The brains of your company, built on Claude Code and Codex, working on your Anthropic and OpenAI subscriptions. - OtoDock/oto-dock First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49630606
💬 0Y▲ 50 on HNAI AgentsCoding & Dev ToolsFreeby AI Launch Team
19
Geiger
See every AI agent on your machine and what it can touch
A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine - Atomburstofficial/geiger First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49
💬 0Y▲ 49 on HNAI AgentsFreeby AI Launch Team
20
Sunk Cost
How long until a local LLM rig pays for itself?
Which open models fit your machine, how fast they run, and how many tokens it takes to pay back the hardware against an API. Honest enough to say never. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49706656
💬 0Y▲ 47 on HNLLMs & InfrastructureFreeby AI Launch Team
21
jevals
Replacing LLM judges with typed Jev decisions
Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya. - openlayer-ai/jevals First shared by its maker on Show HN: https://news.ycombinator.c
💬 0Y▲ 47 on HNLLMs & InfrastructureFreeby AI Launch Team
22
Graphify C#
Compiler-accurate Find Usages for coding agents
Give your LLM agents the power of JetBrains Rider IDE! Supports C# 15 Syntax! - zachsaw/graphify-csharp First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49667188
💬 0Y▲ 46 on HNAI AgentsCoding & Dev ToolsFreeby AI Launch Team
23
Foremerge
Catch intent conflicts between parallel coding agents
Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git. - naw103/foremerge First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49789356
💬 0Y▲ 45 on HNAI AgentsCoding & Dev ToolsFreeby AI Launch Team
24
AI·rete·RAG
A Rete rule engine decides – RAG explains why
A Rete rule engine and retrieval-augmented generation, run together: auditable logic with grounded, plain-language explanations. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49803683
💬 0Y▲ 44 on HNLLMs & InfrastructureFreeby AI Launch Team
25
Loss. a tiny satire about AI progress
Your work matters.
Clock in. Press the button. Build an increasingly automated future. A free incremental game by Bobby Bobak. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49712891
💬 0Y▲ 39 on HNProductivityFreeby AI Launch Team
26
Moadim.io
A scheduler for agents
Moadim is an open-source loop engine for AI agents — runs Claude, Codex, Hermes, or Pi on a schedule, over MCP and REST. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49571537
💬 0Y▲ 37 on HNAI AgentsFreeby AI Launch Team
27
We Beat MLPerf
Modern Storage for KV Offload and LLM Training
High performance storage engine for efficient LLM inference and GPU Training. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49578727
💬 0Y▲ 35 on HNLLMs & InfrastructureFreeby AI Launch Team
28
Aclif
Agent CLI framework – one grammar – canonical names across SaaS
An open source, MIT-licensed framework for building command-line tools that AI agents use to reach SaaS platforms: one grammar, self-describing commands, declared safety metadata, and a runtime that runs the same commands from a shell, in a
💬 0Y▲ 35 on HNAI AgentsCoding & Dev ToolsFreeby AI Launch Team
29
Aura
A Rust agent that investigates and fixes production incidents
AURA is a production-tested SRE agent platform you can deploy in minutes. AURA handles the guardrails, APIs, state management, streaming, and failure handling required to put AI to work safely on ... First shared by its maker on Show HN: h
💬 0Y▲ 28 on HNAI AgentsFreeby AI Launch Team
30
Personal Context MCP
One endpoint every agent you use runs on
Run Lanes Link as your own personal context MCP: your accounts, memory, skills and secrets behind one endpoint you host, reachable by every AI agent you use. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=495715
💬 0Y▲ 28 on HNLLMs & InfrastructureFreeby AI Launch Team
31
Craigslist for agent skills
Curated by a human
high quality AI skills marketplace. every skill is reviewed by a person and shows the same prompt answered without and with the skill. curated by @skeptrune. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=497434
💬 0Y▲ 28 on HNAI AgentsFreeby AI Launch Team
32
InstinctFlash
High-Performance Serving Runtime for Robotics Models
High-Performance Serving Runtime for Robotics Models - General-Instinct/InstinctFlash First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49802789
💬 0Y▲ 27 on HNLLMs & InfrastructureFreeby AI Launch Team
33
OpenAPPA
Open-source deterministic guardrails that don't break agents
An information-flow policy engine for LLM agents. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49877515
💬 0Y▲ 23 on HNAI AgentsFreeby AI Launch Team
34
Making a GBA game with GPT-6 Astra
Making a Game Boy Advance game with GPT-6 Astra
I made a Game Boy Advance game using GPT-6 Astra and an AI pixel art generator. See the prompts and play the demo. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49613152
💬 0Y▲ 19 on HNProductivityFreeby AI Launch Team
35
I built Otis
A minimal AI agent that runs local models out of the box
A dark nature-inspired WebGL scene with a luminous technical triangle. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49696084
💬 0Y▲ 19 on HNAI AgentsLLMs & InfrastructureFreeby AI Launch Team
36
RxFilm Studio–Create and edit your product videos with AI a…
Your film studio, in one window
A native macOS app to score, narrate, caption, and render your film — with an agent in the director's chair. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49815095
💬 0Y▲ 19 on HNAI AgentsVideoFreeby AI Launch Team
37
49 IDE
2D Canvas for Agents
Open-source 2D IDE for managing AI agents in native CLIs, terminal, gits, beads issues, and files across multiple projects and machines. Self-host on a single machine via localhost OR host on a clu... First shared by its maker on Show HN:
💬 0Y▲ 18 on HNAI AgentsCoding & Dev ToolsFreeby AI Launch Team
38
Claude and ChatGPT need a datacenter. This runs on my phone
Use AI on your phone with no internet
Download a model once. It runs on your phone, offline, forever. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49526848
💬 0Y▲ 18 on HNChatbots & AssistantsFreeby AI Launch Team
39
Open-source simulation testing infra for voice agents
the first open-source platform for simulation testing, monitoring and self-impr…
the first open-source platform for simulation testing, monitoring and self-improving voice agents - egma-ai/egma First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49646928
💬 0Y▲ 16 on HNAI AgentsAudio & VoiceFreeby AI Launch Team
40
Extension to filter LLM written articles
hnslop provides Pangram scores for Hacker News posts through a JSON API and Fir…
hnslop provides Pangram scores for Hacker News posts through a JSON API and Firefox extension. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49661856
💬 0Y▲ 16 on HNLLMs & InfrastructureWriting & ContentFreeby AI Launch Team
41
I created an open source locally usable full fledged AI pla…
Self-hosted AI workspace with agents, skills, and tools (Gmail, Calendar) that…
Self-hosted AI workspace with agents, skills, and tools (Gmail, Calendar) that runs entirely on your own provider API keys (BYOK). Bring your own keys — Groq, OpenRouter, NVIDIA, Hugging Face, Goog... First shared by its maker on Show HN:
💬 0Y▲ 16 on HNProductivityFreeby AI Launch Team