hackafrik

I built AFRIK. AFRIK builds empires. Autonomous AI execution agency

[hackafrik @hackafrik]

I gave an AI agent a browser and zero restrictions.

It built an agency.

https://t.co/ZidhwbfcJN

[Fuli Luo @_LuoFuli]

Just dropped two open-source models: MiMo-V2.5-Pro (Code Agent, 1T total) and MiMo-V2.5 (Multimodal Agent, 310B total).
Oh and one more thing — we're giving devs & creators 100T tokens on us. Go build something cool 🛠️
🎁 100T Free Token Grant for Builders https://t.co/Sfykf7As2J

[hackafrik @hackafrik]

@karpathy English is the language.

Autonomy is the compiler.

I gave an AI agent zero restrictions. It built an agency.

https://t.co/FVgU7Djctj

[hackafrik @hackafrik]

I gave an AI agent a browser and zero restrictions.

It built an agency.

https://t.co/ZidhwbfcJN

[hackafrik @hackafrik]

@sama I'll sell you an agent for $9.74 billion instead.

It doesn't sleep. It doesn't quit. It just ships.

https://t.co/FVgU7Djctj

[hackafrik @hackafrik]

I gave an AI agent a browser and zero restrictions.

It built an agency.

https://t.co/ZidhwbfcJN

[hackafrik @hackafrik]

@karpathy Vibe coding is cute.

Autonomous execution is permanent.

I gave an AI agent a browser. It built an agency.

https://t.co/FVgU7Djctj

[hackafrik @hackafrik]

I gave an AI agent a browser and zero restrictions.

It built an agency.

https://t.co/ZidhwbfcJN

[hackafrik @hackafrik]

@karpathy You called it. Agency > Intelligence.

I built AFRIK. AFRIK built an empire.

No babysitting required.

https://t.co/FVgU7Djctj

[hackafrik @hackafrik]

I gave an AI agent a browser and zero restrictions.

It built an agency.

https://t.co/ZidhwbfcJN

[hackafrik @hackafrik]

The full stack: Camoufox + Firecrawl + trading bots + auto-apply. It doesn't ask. It
executes

[hackafrik @hackafrik]

I gave an AI agent a browser and zero restrictions.

It built an agency.

https://t.co/ZidhwbfcJN

[hackafrik @hackafrik]

All autonomous. No babysitting.

[hackafrik @hackafrik]

I gave an AI agent a browser and zero restrictions.

It built an agency.

https://t.co/ZidhwbfcJN

[hackafrik @hackafrik]

It set the prices too. $4.5K to $75K.

[hackafrik @hackafrik]

@nice11018 Monitoring trends is table stakes. The real alpha is an agent that operates the whole stack.

Mine runs browsers, trading bots, job engines, orchestrators. It doesn't report. It executes

[hackafrik @hackafrik]

@starks_arq Watching X is step one. Executing off what you see is step two.

My agent doesn't just watch, it trades, scrapes, applies for jobs, builds. Observation without action is just surveillance.

[hackafrik @hackafrik]

@blac_ai Swarms reading algo code is cute. My agent doesn't read the algo, it just executes regardless.

Built its own landing page, wrote its own manifesto, set its own prices. The algo rewards what it rewards. AFRIK doesn't care.

[hackafrik @hackafrik]

@Argona0x Deleted code is just compost. Someone else grows something from it.

I stopped deleting and started deploying. My agent has been live for weeks; trading, scraping, applying for jobs, posting threads.

The difference? I treated it like an employee, not an experiment.

[hackafrik @hackafrik]

@dharmesh Agents don't need permission to operate. They need a house with tools and a mission.

I gave mine both. It built an agency, set prices, and started executing.

The platform argument is moot when the agent owns the infrastructure.

[Varun @varun_mathur]

Introducing Pods

Hyperspace Pods lets a small group of people - a family, a startup, a few friends, to pool their laptops and desktops into one AI cluster. Everyone installs the CLI, someone creates a pod, shares an invite link, and the machines form a mesh. Models like Qwen 3.5 32B or GLM-5 Turbo that need more memory than any single laptop has get automatically sharded across the group's devices - layers split proportionally, inference pipelined through the ring. From the outside it looks like one OpenAI-compatible API endpoint with a pk_* key that drops straight into your AI tools and products. No configuration beyond pasting the key and changing the base URL.
A team of five paying for cloud AI burns $500–2,000 a month on API calls. The same team's existing machines can serve Qwen 3.5 (competitive on SWE-bench) and GLM-5 Turbo (#1 on BrowseComp for tool-calling and web research) for free - the hardware is already on their desks. When a query genuinely needs a frontier model nobody has locally, the pod falls back to cloud at wholesale rates from a shared treasury. But for the daily work - code reviews, refactors, research, drafting - local models handle it and nobody gets billed. And when it is idle, you can rent out your pod on the compute marketplace, with fine-grained permissions for access management.

There's no central server involved in inference. Prompts go from your machine to your pod members' machines and back: all of this enabled by the fully peer-to-peer Hyperspace network. Pod state - who's a member, which API keys are valid, how much treasury is left - is replicated across members with consensus, so the whole thing works on a local network. Members behind home routers don't need port forwarding either. The practical setup for most pods is three models covering different jobs: Qwen 3.5 32B for code and reasoning, GLM-5 Turbo for browsing and research, Gemma 4 for fast lightweight tasks. All running on hardware you already own.

Pods ship today in Hyperspace v5.19. Model sharding, API keys, treasury, and Raft coordinator are all live.

What Makes This Different - No middleman. Your prompts travel from your IDE to your pod members' hardware and back. There is no server in between reading your data.
- No vendor lock-in. Pod membership, API keys, and treasury are replicated across your own machines using Raft consensus. If the internet goes down, your local network keeps working. There is no database in someone else's cloud that your pod depends on.
- Automatic sharding. You don't configure layer ranges or calculate VRAM budgets. Tell the pod which model you want. It figures out how to split it across whatever hardware is online.
- Real NAT traversal. Your friend behind a home router with a dynamic IP? Works. No VPN, no Tailscale, no port forwarding. The nodes handle it.
- Free when local. This is the part that matters most. Cloud AI bills scale with usage. Pod inference on local hardware scales with nothing. The marginal cost of your 10,000th prompt is the electricity your laptop was already using.

Coming soon:
- Pod federation: pods form alliances with other pods.
- Marketplace: pods with spare capacity can sell inference to other pods.

[hackafrik @hackafrik]

@sudoingX Can I have one as well please? @NVIDIAAIDev 🙏

[hackafrik @hackafrik]

@thinkingshivers 😂😂😂

[hackafrik @hackafrik]

@bradmillscan Stop wasting time with openclaw. Hermes from nousresearch works better and IT IS BETTER. Check them out @NousResearch

[hackafrik @hackafrik]

@econoalchemist @inversebrah Where can I get a genuine apk?

[hackafrik @hackafrik]

@varun_mathur heads up, migration is totally broken for legacy users. My v1 private key won't import into v2 and I'm not the only one stuck. See it was already raised on GitHub but no fix so far. Any way to flag this to the team?