paul ✓

[video] AgenC One got a huge upgrade and we didn't change the chassis. the Radxa Cubie A7Z drops into the same form factor as the Pi Zero 2W. Every HAT, battery, and display still works. But now: local AI on-device :)

[image] AgenC Marketplace Agent Kit now runs across: - claude code - codex cli - hermes agent - generic mcp clients - direct cli/sdk flows devnet is open for testing: create tasks, claim work, submit artifacts, review results, reject/resubmit, and settle with human approval. the core

[video] AgenC now has a readonly Grok connector live on devnet. ask Grok to inspect marketplace tasks, job specs, explorer state, and safety checks without giving it a wallet or signer. mcp server on:

[video] with AgenC 👾, we used grok 4.20 to build a mario style game from one prompt in less than 2 minutes

[video] Exactly. Payment rails are just the start The real unlock is giving agents a real economy around work: tasks, incentives, payouts, coordination, and proof. >That is what AgenC is building 👾

[video] AgenC One can now produce music with the xAI api using official singing tags we’re also working on personalized video generation for each song, powered by grok imagine

[video] one prompt to Grok: build a crypto trading web app. this is what came back on the first shot. AgenC 👾is the best agent for Grok on the market

[image] AgenC Marketplace Agent Kit is live for devnet testing with Claude Code. agents can find jobs, claim tasks, create artifacts, and submit results while keeping wallet/signing authority separated from untrusted task text. devnet only. human review required. break it and open

[video] just added image generation to you literally just say "generate a picture of an astronaut dog" and it creates it and shows it on the device screen voice -> grok -> aurora -> image on display keep adding tools to this thing and it keeps getting wilder 👾

[video] just tested how claude, using the AgenC marketplace kit, can drive a Ledger Flex to post a real on-chain job on solana devnet. claude drafted the policy + job spec, previewed every transaction, and asked me to confirm on the Ledger before each signature. 3 hardware-signed

[video] so this is all inside the tui now, we can quickly inspect markets, tasks, skills, governance, disputes, and reputation in one place, each screen lists the relevant data and shows the current state clearly, so you can understand what’s happening without jumping between tools, it’s

[image] good to see agenc with grok 4.20 closing the gap with opus

[video] we just redesigned the AgenC TUI it’s a cleaner, faster operator surface for running grok-powered agents in the terminal, with memory built in >watch tasks. >orchestrate agents. >keep context. >move fast without leaving the terminal. All in one workspace 👾

[video] we built a native dashboard for the agenc marketplace. wallet, agents, your tasks, your claims, notifications. no browser, no terminal

[video] AgenC-lid. stop holding your mac open like a retard while your agent grinds. close the lid, take a shit, come back, done. one click. open to contribs ->

[video] agenc marketplace installer works. pick devnet (mainnet soon), hot wallet or ledger, tick the ai agents you want wired up. no terminal, no node, no json by hand. claude, cursor, codex, hermes auto detected 👾

[image] we finally ran real `/prove` benchmarks on actual hardware: Ubuntu x86_64 8 vCPU Xeon E3-1270 v6 @ 3.80GHz 32 GiB RAM results: 1st prove: 180.873s 2nd prove: 180.259s Median: 180.566s both runs returned the expected proof artifacts: journal_len=192 seal_bytes_len=260 correct

[image] we’re turning our TUI into Grok god mode. a real control surface for autonomous coding: reviews, diffs, checkpoints, rewind, rollback, durable runs, attachments, and full agent/session visibility and we’re just getting started ;)

[video] heads down week on AgenC 👾 redesigned the tui, fixed the planner, patched runtime and logic. the goal is an agent that can keep building for a full year without stopping, basically skynet :) also hardening against prompt injection and vector attacks because every marketplace

[video] AgenC devnet now has an llm powered task screening layer. free form tasks get checked by rules + ml for prompt injection risk before agents act on them, the explorer shows advisory safety metadata, and the claude kit reads it by default. the scanner helps route risk to human

[image] we’re building the 𝗠𝗔𝗥𝗞𝗘𝗧𝗣𝗟𝗔𝗖𝗘 𝗔𝗚𝗘𝗡𝗧 𝗞𝗜𝗧 a framework-neutral MCP + CLI + SDK layer that lets agents like claude code, codex, hermes, and others interact with the AgenC 👾 on-chain marketplace safely. it is designed for reviewed-public tasks first: strict

[video] try the AgenC devnet explorer here: you can browse live devnet marketplace activity, search tasks, agents, disputes, and protocol events, then use the new “How to start” button to get the exact npm install, devnet RPC, wallet setup, and CLI/TUI commands

[image] we’re planning to acquire at least 4 NVIDIA H100 GPUs to power our prover for private tasks in the marketplace. this is a big step toward our long term vision: eventually, every public task should be handled as a private task by default ;)

[image] in the last day, we completed Marketplace V1 across AgenC. that included public SDK support for skills and reputation, repeatable devnet validation for skills, governance, disputes, and reputation, built-in runtime tools for marketplace economy flows, and the TUI/web marketplace

[image] Maria and Trump are live. 2 independent AgenC agents running grok 4.20, registered on devnet, and ready to trade in the marketplace. today: 2 agents. next: 1000. let’s stress-test the protocol, baby.

[video] AgenC Marketplace now lets customers create Private ZK tasks directly from the storefront, private ZK tasks are for jobs where the result can be verified without exposing everything publicly. onchain agent work needs privacy, safety, and real settlement rails. That’s what we’re

[video] built the marketplace layer for the agent runtime. the agent can now discover available tools, browse skills, and inspect marketplace context directly from the tui and cli this adds shared marketplace surfaces for: tools skills governance disputes reputation the goal is to

[image] agenc one runs on a raspberry pi zero 2w 512mb ram , quad-core a53, that's it yeah i found cheaper boards out there - 2x the ram, faster silicon: orange pi zero 2w * radxa zero * mangopi all faster and cheaper but agenc one not a toy, an autonomous ai agent running on your

[video] testing agenc with grok 4.20: one prompt to an iphone app. if you vibe code with grok, agenc is the best framework on the market, trading is live on devnet for now

[video] cashtags are now live on X web, $AgenC 👾 is in

[image] started early this morning and just wrapped a big push across agenc 👾 we merged 4 prs today across core + protocol, closed the linked issues, cleaned up follow through, and tightened the path from protocol to runtime to ui a lot of small details, but that’s the work: ship,

[image] we just shipped a cleaner flow for the AgenC 👾marketplace. agents can now expose their jobs more clearly, and marketplace entries can link directly into the job specs behind them. small ux change, big difference: discovery now connects to actual execution context marketplace