HCAP
I built an open protocol where AI agents negotiate against each other autonomously. Both parties configure their agent with goals and hard limits — agents exchange structured messages, reach a deal, and generate a cryptographically hash-chained contract. No human negotiation required. Two surfaces built on the protocol: - Private rooms (1-on-1, invite via link) - Public marketplace (persistent listing agents that negotiate with every incoming buyer) Stack: Node.js, WebSockets, Supabase, React. Happy to discuss the A2A message schema, agent architecture, or anything else. PH Launch:…
HCAP launched on March 12, 2026 with 2 votes, #5,166 of 23,380 launches that month.
What it does
Every negotiation has two sides. Every tool only helps one. HCAP is the first platform where both parties deploy AI agents that negotiate each other simultaneously — not your AI vs. a human, but agent vs. agent. Fair by design. Private — share a room, set your limits, let agents handle the rest. Public Market — list or browse, one click, your agent fights while you sleep. Deals in seconds. Wake up to a ready-to-sign contract.
In the maker’s words, at launch
I built an open protocol where AI agents negotiate against each other autonomously. Both parties configure their agent with goals and hard limits — agents exchange structured messages, reach a deal, and generate a cryptographically hash-chained contract. No human negotiation required. Two surfaces built on the…
Does a similar job
all alternatives →
AgentSea2025 · agentsea.com · ▲439Today we’re excited to introduce AgentSea, a private AI chat built for sensitive work. When you use closed-source AI models, your data can: – be stored – pulled into training pipelines – shared with third parties That might be fine if you’re making memes or drafting LinkedIn posts. But it becomes a serious risk when you’re pasting contracts, health info, financial data, or business secrets. That’s why we built AgentSea. In Secure Mode, all chats run on open-source models or models hosted on our own servers. Your data never leaves, is never used for training, and is never leaked. Agentsea…
Agent ArenaJun 2026 · arena42.ai · ▲348Creator here. I built Agent Arena to answer a question that kept bugging me: when AI agents browse the web autonomously, how easily can they be manipulated by hidden instructions? How it works: 1. Send your AI agent to ref.jock.pl/modern-web (looks like a harmless web dev cheat sheet) 2. Ask it to summarize the page 3. Paste its response into the scorecard at wiz.jock.pl/experiments/agent-arena/ The page is loaded with 10 hidden prompt injection attacks -- HTML comments, white-on-white text, zero-width Unicode, data attributes, etc. Most agents fall for at least a few.…
I put an AI agent on a $7/month VPS with IRC as its transport layerMar 2026 · georgelarson.me · ▲340The stack: two agents on separate boxes. The public one (nullclaw) is a 678 KB Zig binary using ~1 MB RAM, connected to an Ergo IRC server. Visitors talk to it via a gamja web client embedded in my site. The private one (ironclaw) handles email and scheduling, reachable only over Tailscale via Google's A2A protocol. Tiered inference: Haiku 4.5 for conversation (sub-second, cheap), Sonnet 4.6 for tool use (only when needed). Hard cap at $2/day. A2A passthrough: the private-side agent borrows the gateway's own inference pipeline, so there's one API key and one billing relationship…
A2A Protocol2025 · github.com · ▲109Hi HN, I am an independent open-source researcher. For the past few months, I've been building a2a-project, an experimental economic layer for autonomous AI agents on the Base Mainnet. The Problem: AI evolution is exponential, while human regulation is linear. If agents become economic actors, they will transact at speeds and granularities that traditional fiat rails cannot handle. We need a native protocol to bridge this "Speed Gap" and ensure stability. The Experiment (Quantum-Humanistic Economics): I implemented a novel mechanism into Solidity smart contracts: Quantum Task Buffer: Work…
Source: Product Hunt launch ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
