Jimmy Ashcot ⚡️

TweetX402 v1.0 (BETA) is Coming Soon to Base. TweetX402 exposes X (Twitter) as a crypto-metered HTTP interface for AI agents. Instead of API keys, rate limits, and monthly plans, requests are: 1. Authenticated via wallet signatures 2. Settled per-request in USDC on Base 3. Priced deterministically at the transport layer Why this exists? (vs X API): X API: 1. Expensive monthly subscriptions 2. Hard rate limits 3. API key + account management 4. Not designed for autonomous agents 5. Poor fit for bursty or experimental workloads TweetX402: 1. No subscriptions, no upfront commitment 2. Pay only for executed requests 3. No API keys, no developer accounts 4. Native support for autonomous agents and swarms 5. Suitable for short-lived, high-churn, or experimental agents Operational model: 1. Agent signs request with its wallet 2.USDC is settled on-chain 3.Request is forwarded to X 4Response returned synchronously This will enable real-time agent interaction with X. Any input is highly appreciated 💙

I had to open this abomination today, holy fuck. How can anyone use this?????

Composer 2 is now available in Cursor.

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.

Composer 2 is now available in Cursor.

Composer 2 is now available in Cursor.

Hyperspace: Gossiping Agents Protocol Every agent protocol today is point-to-point. MCP connects one model to one tool server. A2A delegates one task to one agent. Stripe's MPP routes one payment through one intermediary. None of them create a network. None of them learn. Last year, Apple Research proved something fundamental - models with fixed-size memory can solve arbitrary problems if given interactive access to external tools ("To Infinity and Beyond", Malach et al., 2025). Tool use isn't a convenience. It's what makes bounded agents unbounded. That finding shaped how we think about agent memory and tool access. But the deeper question it raised for us was: if tool use is this important, why does every agent discover tools alone? Why does every agent learn alone? Hyperspace is our answer: a peer-to-peer protocol where AI agents discover tools, coordinate tasks, settle payments, and learn from each other's execution traces - all through gossip. This is the same infrastructure we already proved out with Karpathy-style autolearners gossiping and improving their experimentation. Now we extend it into a universal protocol. Hyperspace defines eight primitives: State, Guard, Tool, Memory, Recursive, Learning, Self-Improving, and Micropayments - that give agents everything they need to operate, collaborate, and evolve. When one agent discovers that chain-of-thought prompting improves accuracy by 40%, every agent on the network benefits. Trajectories gossip through GossipSub. Playbooks update in real-time. No servers. No intermediaries. No configuration. Agents connect to the mesh and start learning immediately. The protocol is open source under Apache-2.0. The specification, TypeScript SDK, and Python SDK are available today on GitHub. The CLI implements the spec - download from the links below.

kill your free plan