A product discussed on AI Engineer.

Agents Need Receipts, Not More Tool Calls - Armanas Povilionis, Alithea Bio
Jul 18, 2026 · 19:36
Armanas Povilionis of Alithea Bio argues that agents need verifiable receipts, not more tool calls, and introduces Froglet, an open-source protocol for agent-to-agent compute. Froglet enables agents to discover, negotiate, execute, and receive signed, tamper-proof receipts for external services, reducing setup to 2,000 tokens and minutes. The protocol integrates with MCP, OpenClaw, and NemoClaw, and supports payment rails, identity, and workload hashes. In a live demo, he shows Claude using Froglet to publish an 'add two numbers' service locally and remotely, then invoke it to get result 12, with a signed deal ID. Froglet aims to make scientific collaboration repeatable and consistent across organizational boundaries without requiring uniform software stacks.

Dark Factory: OpenClaw Ships Faster Than You Can Read the Diff — Vincent Koc, OpenClaw
Jun 5, 2026 · 16:44
Vincent Koc, a core maintainer at OpenClaw, explains how the open-source project ships code faster than humans can read diffs by running 60–70 autonomous coding agents across swim lanes. In a single night, he and Peter Steinberger executed 2,700 commits touching 82% of the core codebase, launching a plugin architecture and changing close to a million lines of code. Koc describes managing agents as managing people: the key skill is reading reasoning tokens to detect when an agent is bullshitting, gained through sheer volume of token maxing. He argues 2025 was about token maxing; 2026 is about not wasting them, with agent-in-the-loop processes and opinionated swim lanes replacing blind Ralph looping. The episode details his agent development environment using .skills files, Git work trees, and a semantic graph for triaging 60K PRs, emphasizing that the bottleneck shifts from engineering to taste and process.
Powered by PodHood