NanoAgent, zero-dependency 1k-LOC AI-agent runtime
The nano framework for AI agents. Pure TypeScript, no dependencies, 100x smaller than langchain. - hbbio/nanoagent
NanoAgent, zero-dependency 1k-LOC AI-agent runtime launched on April 28, 2025 with 12 votes, #2,465 of 7,818 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 1 year on.
In plain words
NanoAgent is a lightweight AI-agent runtime written in under 1,000 lines of code with no external dependencies. It enables developers to build and run AI agents with minimal overhead and setup complexity. The platform is designed for developers who need a simple, self-contained solution for creating autonomous AI systems without relying on heavy frameworks or third-party packages.
written from the facts on this page · September 2026
From the sources
NanoAgent is a micro‑framework (≈ 1 kLOC) for running LLM‑powered agents in pure TypeScript with zero runtime dependencies outside of bun . You only need your favorite chat models: OpenAI, or a local engine like Ollama. Why another agent runtime? Model Context Protocol (MCP) is bringing the opportunity to de-clutter agent frameworks. Most features should be tools, retrieval sources, etc. in a standard JSON envelope, then hand that context to any model. NanoAgent focuses on one job: the control loop and leaves RAG, vector search, databases and cloud calls to MCP‑compatible tools. The result is a tiny, transparent core you can audit in an afternoon. Note that this projects implements a few…from github.com
Does a similar job
all alternatives →
NanoClaw – “Clawdbot” in 500 lines of TS with Apple container isolationFeb 2026 · github.com · ▲533I’ve been running Clawdbot for the last couple weeks and have genuinely found it useful but running it scares the crap out of me. OpenClaw has 52+ modules and runs agents with near-unlimited permissions in a single Node process. NanoClaw is ~500 lines of core code, agents run in actual Apple containers with filesystem isolation. Each chat gets its own sandboxed context. This is not a swiss army knife. It’s built to match my exact needs. Fork it and make it yours.
- OHOne Human + One Agent = One Browser From Scratch in 20K LOCJan 2026 · emsh.cat · ▲324
Related: https://simonwillison.net/2026/Jan/27/one-human-one-agent-on...
Xcode 26.3Feb 2026 · developer.apple.com · ▲319Leverage coding agents to tackle complex tasks autonomously
Microagents: Agents capable of self-editing their prompts / Python code2023 · github.com · ▲221Agents Capable of Self-Editing Their Prompts / Python Code - aymenfurter/microagents
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗
Launched alongside, April 2025
the whole month →
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
The Unsure Calculator is an online tool that lets you calculate with numbers you’re not sure about.
Life & fun · 2025 · filiph.github.io
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
