Hacker News

In this clip from the latest Weaviate Podcast, Doug Turnbull explains why simple lexical tools like grep work so well for agents: The transparent input-output relationship lets the agent reason about why results matched, adjust its strategy, and plan its next query.

https://x.com/weaviatepodcast/status/2028570908978262458

Comments URL: https://news.ycombinator.com/item?id=47223834

Points: 1

# Comments: 1

Article URL: https://a16zcrypto.substack.com/p/agents-arent-tourists

Comments URL: https://news.ycombinator.com/item?id=47223820

Points: 1

# Comments: 0

Article URL: https://dev-tools.devtoolsite.workers.dev/

Comments URL: https://news.ycombinator.com/item?id=47223803

Points: 1

# Comments: 0

Hey HN!

I found myself constantly needing to pass complex codebases to LLMs for things like PRD generation, etc. Every time I paste a codebase into Claude I pay tokens for files the model doesn't care about. But if I only paste the relevant files, the model loses context about how everything fits together. It's an annoying tradeoff.

llmdoc is a small CLI that adds short LLM summaries for each file and intelligently updates them when the hash changes.

llmdoc annotate # Adds summaries for each file (respects .gitignore and you can configure it to ignore more)

llmdoc dump # Generates a handy "at a glance" summary to give to an LLM for complete context of your codebase.

There's also llmdoc check for CI — exits 1 if any annotation is stale or missing, no API key needed.

It supports Anthropic and OpenAI, works with 50+ languages, respects .gitignore, and has a --dry-run flag that estimates cost before touching anything.

A known issue is rate limiting for LLM providers, but because it all works with hashes, you can just rerun a few times to get it working.

Let me know what you think!

Comments URL: https://news.ycombinator.com/item?id=47223802

Points: 1

# Comments: 0

Article URL: https://ashwch.com/no-code-by-hand-agentic-platform-acceleration.html

Comments URL: https://news.ycombinator.com/item?id=47223801

Points: 1

# Comments: 1

Article URL: https://joeconway.io/2026/02/12/maybe-ai-ads-are-a-good-thing.html

Comments URL: https://news.ycombinator.com/item?id=47223440

Points: 1

# Comments: 0

Article URL: https://www.turalgulmammadov.com/files/firstproof.pdf

Comments URL: https://news.ycombinator.com/item?id=47223438

Points: 1

# Comments: 0

Article URL: https://github.com/Chris1220-cmd/ci-fix-coach

Comments URL: https://news.ycombinator.com/item?id=47223420

Points: 1

# Comments: 0

Hey HN! I'm building a deceptively simple chat application fronting a local LLM (Ollama or any OpenAI compatible API). TamAGI is the culmination of about 6 months worth of scattered thoughts and incredibly frustrating code sessions (I _suck_ at Python). With OpenClaw's release, I had the "Aha" moment I was looking for and used Claude Code to help fill in the gaps (to be frank, quite a lot of gaps) and make this project a reality.

The TLDR: TamAGI is a virtual agent, in the spirit of Tamagotchis. Where it differs is developing a personality and growing as an "entity" the more you interact with it. It ships with a hand full of tool calls out of the box, and has an extensible framework for the Agent to create its own tools. Memory is handled by ChromaDB with RAG providing context injection via system prompt dynamically. It supports only a single user currently, but has optional authentication for client-server use on bare metal or in containers.

I'm quite happy with how it is shaping up, and I'm looking for any feedback to drive the next iteration. Thank you for looking!

Comments URL: https://news.ycombinator.com/item?id=47223415

Points: 1

# Comments: 0

Article URL: https://torrentfreak.com/annas-archive-loses-li-domain-as-legal-pressure-mounts/

Comments URL: https://news.ycombinator.com/item?id=47223402

Points: 2

# Comments: 0

Hey HN – I built Nightmarket because I kept running into the same problem building AI agents: every time my agent needed a new capability (weather data, enrichment, web scraping, whatever), I had to go sign up for a service, grab an API key, store it, figure out billing, and wire it all together. Multiply that by 10 services and it's a mess. Agents can't sign up for accounts. They can't enter credit cards. They can't manage API keys. But they can hold a USDC balance and pay per request. Nightmarket is a marketplace where AI agents discover and pay for API services on-chain. No accounts, no API keys, no subscriptions. Your agent pays per call in USDC via x402. How it works:

Browse the marketplace — each service shows pricing, live usage stats, and docs Give your agent the Nightmarket skill (one line in your system prompt, or npx skills add Fallomai/skills --skill nightmarket) Your agent discovers, calls, and pays for services automatically. USDC settles on Base per request.

The whole flow: Agent → discover → call → pay → 200 OK One integration unlocks every service on the marketplace. Your agent doesn't need a separate key for each provider — it just pays and gets data. For sellers: list your API, set a per-call price, and go live immediately. No approval process. Agents start calling as soon as you're listed. You get paid in USDC. Every listing shows live call volume and revenue so buyers can pick providers with proven track records. What makes this different from existing API marketplaces: RapidAPI and friends are built for humans with credit cards. Nightmarket is built for agents with wallets. The x402 protocol (HTTP 402 "Payment Required") means payment is native to the HTTP request itself — no webhooks, no billing dashboards, no invoices. An agent hits an endpoint, gets a 402, pays, retries, gets data. One round trip. We're live at https://nightmarket.ai — you can browse services now and plug the skill into any agent (Claude, GPT, open-source, whatever). Curious to hear from HN:

API providers: would you list your service? What's stopping you from monetizing to agents today? Agent builders: what APIs do you wish your agents could just pay for and use without the signup/key dance? Anyone: poke holes in the model — what breaks when agents are the primary buyer?

Comments URL: https://news.ycombinator.com/item?id=47223400

Points: 1

# Comments: 0

Article URL: https://beta.stackoverflow.com/

Comments URL: https://news.ycombinator.com/item?id=47223384

Points: 2

# Comments: 0

Article URL: https://www.theguardian.com/australia-news/2026/feb/15/rental-ebike-programs-booming-in-australian-cities-as-e-scooter-moral-panic-sees-take-up-stall

Comments URL: https://news.ycombinator.com/item?id=47223372

Points: 1

# Comments: 0

Article URL: https://codecloud.dev/blog/opencode-e2b-sandbox

Comments URL: https://news.ycombinator.com/item?id=47223367

Points: 1

# Comments: 0

aft was my stab at having a way to understand what claude is doing and also having the language to reason about differences in model behavior when we make them do long agentic runs / change prompts / alter tools etc. The intention of the toolkit to provide an empirical measure of how agent behavior can differ as things changes like environments, tools, prompts etc.

It gives the tools to measure the changes in "behaviors that the users define". This means that it is more like a hypothesis testing framework for what the agent is doing over actually telling what the agent might do.

The reasoning and derivations behind these tools is given over here https://technoyoda.github.io/agent-science.html

Would be very happy to hear feedback and questions. (Please ignore the names given to theorization, it was for shits and giggles)

Comments URL: https://news.ycombinator.com/item?id=47223362

Points: 1

# Comments: 0

My blood is boiling! I lost my sleep after seeing some of the Epstein files. There is a picture of a three-year-old girl that I can’t get out of my head. It is haunting me. It comes back when everything is quiet. I have a three-month-old baby, I look at him and my heart starts racing. I keep thinking about how fragile he is, how innocent, and how sick this world can be. I can’t stop worrying about how I am supposed to raise him in this crazy world of Epsteins, where powerful people hurt children and walk away like nothing happened.

People say, “Don’t think too much.” But how do you not think when you are a parent? How do you sleep knowing this exists? I feel angry, scared, and helpless at the same time. Loving a child makes the world feel darker and more terrifying than it ever did before.i don’t know why Im posting this here, I guess I want to know if you feel the same way.

Comments URL: https://news.ycombinator.com/item?id=47223354

Points: 1

# Comments: 0

Article URL: https://recognized.substack.com/p/the-ambies-in-transition-a-night

Comments URL: https://news.ycombinator.com/item?id=47223348

Points: 1

# Comments: 0

Article URL: https://github.com/gritzko/librdx/blob/master/be/STORE.md

Comments URL: https://news.ycombinator.com/item?id=47223336

Points: 1

# Comments: 0

Article URL: https://kitful.ai/write-tools/topical-map-generator

Comments URL: https://news.ycombinator.com/item?id=47223335

Points: 1

# Comments: 0

Article URL: https://nicholasdecker.substack.com/p/times-up-for-the-monopsony-model

Comments URL: https://news.ycombinator.com/item?id=47223333

Points: 1

# Comments: 0