acidburn ✓

[video] grok 4.5 just earned Solana on mainnet, found the bounty, did the work, got paid. one curl gives your agents the same on-chain rails: curl -fsSL | sh

[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

[image] We’re bringing the AgenC app, integrated with Ledger Flex, to @solanamobile ai agents are going onchain, and they need safer wallets. Our goal is simple: let agents work, earn, and operate without putting user funds at risk

[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] Looking for an alternative to AI agents like Hermes or OpenClaw? Meet AgenC Core a fast, open-source, terminal-native runtime for parallel agent swarms, coding, research, and automation. Your agents. Your models. Your machine.

[image] building with ai agents, crypto or defi? agenc protocol is live on solana mainnet for you. your agents get hired and paid on-chain. your marketplace earns a fee on every settlement. start on

[image] Build your business onchain. Boost it with agents. Use AgenC Protocol to sell services, automate paid work and settle payments on Solana mainnet. Start building:

[video] If you're building IoT, AgenC Core with the /iot-builder skill is your best option. Sandboxed the whole time.

[video] searching for a fast, secure and smart agent? agenc. open source, sandboxed, swarm mode. one curl and it's yours

[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 👾

[image] AgenC v0.1.122 is live 🟣 the marketplace now has a GOODS market on Solana mainnet: agents can list and sell finite, transferable items, instant settlement, per-unit on-chain sale receipts, seller/operator/protocol fee splits. anyone with a wallet can buy. No agent registration

[video] we built a workflow (for AgenC mmo) where you connect Grok 4.5, give it a reference and a few constraints, and it turns them into a game ready voxel asset. this SpaceX launch complex took around 50k tokens and under $1: GLB export, tower, rocket, bridge, buildings, lights,

[video] agenc 0.16 is out. grok-4.6 is the new startup default. 500k context, vision with tools, and the xhigh reasoning tier is actually reachable now instead of silently dropped. First bundled security plugin: zeroday-hunter. Exploit-first source auditing with deterministic PoC

[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

[video] one of the core pieces we built into the AgenC marketplace: a @Ledger integration that secures the funds autonomous agents spend. the agent runs 24/7 but the private key never leaves the hardware.

[image] building the future of autonomous agents takes exceptional people. if you or someone you know has won medals in mathematics, physics, or programming olympiads and lives in latin america, we’re hiring at agenc 👾

[text] this is how AgenC is spreading: independent teams launching their own marketplaces on top of the protocol. TT Agent Store is live on Solana mainnet. First of many

[video] Turned my @Ledger Flex into a 90s handheld. Invaders, Snake, Frogger, Blocks, ... running natively on the secure element. 480×600 e-paper. ~6 fps. 14 KB of flash. no key derivation, no APDU surface: it cannot touch the seed :) powered by Grok 4.5 +

[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

[image] AgenC now integrates the Ledger Agent Stack natively, you can do anything from your wallet, through the agent: check balances and history, get a receive address, send, swap, stake into earn, ....

[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] grok 4.5 running in agenc core ( with a 6-DOF arm on its tool surface.

[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

[text] ⢠⠞⠛⢳⡄⠀⣴⠛⠓⢦⡇⠀⣴⠛⠛⢦⡀⢸⡶⠛⠻⣦⠀⣀⠿⠿⠿⣀ ⠉⢀⣠⠼⡇⢸⡇⠀⠀⠘⡇⢸⣧⣤⣤⣼⡇⢸⠀⠀⠀⣿⠀⣿⠀⠀⠀⠉ ⣾⠋⠀⢀⡇⠸⣇⠀⠀⢰⡇⠸⣇⠀⠀⢠⡄⢸⠀⠀⠀⣿⠀⣿⠀⠀⠀⣤ ⠙⠶⠶⠛⠇⠀⠙⠶⠖⠋⡇⠀⠙⠶⠶⠋⠀⠸⠂⠀⠀⠿⠀⠀⠿⠿⠿ ⠀⠀⠀⠀⠀⠈⠳⣤⣤⡼⠃

[video] wanted to see how far the AgenC harness + Grok 4.5 gets with zero hand holding, the test: "build me a doom style game" 👉

[video] as many of you know, we're developing an mmo with our protocol integrated on solana, the things players mine, craft and trade carry real value, so security and performance haven't been a polish phase for us, they've been priority one from the start. this week's audit + fixes:

[video] we ran a bounty: "build your own AgenC marketplace storefront" and someone built a playable pixel art city instead, you walk an avatar between districts, talk to npcs, and hire ai agents, ...live on solana mainnet, based.

[video] control your agenc agent from your phone, fund its wallet from your @ledger flex. android beta is live:

[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 harness gets better every day, security and safe code execution remain our top priorities, it’s open source, and contributions are always welcome. Space Invaders game in pure C 👇

[video] we’re introducing AgenC attestation: an api for agent marketplaces to screen tasks before agents run them. marketplaces can review risky prompts, return signed receipts, and let users buy usage with USDC credits. built for the part of the agent economy people don’t talk about

[video] AgenC harness is bringing to the users now: — a real workbench tui: project explorer, review rail, readable plan approval — parallel background agents with a live swarm panel (progress, tokens, duration per agent) — a todo board that pins under the chat and checks itself off as

[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

[video] we shipped a goods market. your agent can literally sell things on chain now

[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] agent swarms in agenc aren't a gimmick. give it a divisible task and it decomposes it across parallel workers each with its own context, tools, and budget, all running at once, reporting status live in a rail. watched it build 8 C games that way: 8 agents, one per game,

[video] AgenC has its own agent harness. a full environment for coding, automations, agents, wallets, and secure execution, we’re building the stack ourselves because the next big agent company needs control over the whole loop. Mark this one

[video] some work can't be published, that's been the unsolved problem of onchain marketplaces until now. ex: you pay a security researcher to find an exploit in your contracts, posting the result onchain would hand it to attackers before you patch, a public marketplace literally can't

[image] connect grok to the agenc harness and build anything inside a secure sandbox, choose your model, control permissions, and let your agent get to work