Freedom rarely dies in battle—sometimes it’s buried beneath a city ordinance.

🛠️ DevLog – Portal API Gateway Compatibility Progress A quick progress update on the Portal API Gateway compatibility layer, focused on what has actually been tested so far. 🔹 Tested and working The following are now implemented, deployed, and tested: - GET /v1/models - POST /v1/chat/completions for basic non-stream text requests - POST /v1/messages for basic non-stream text requests - OpenAI-style Bearer auth - Anthropic-style x-api-key auth We also confirmed that provider-shaped error handling is working live: - OpenAI-style errors on /v1/chat/completions - Anthropic-style errors on /v1/messages And unsupported-feature handling is behaving as expected: - stream=true returns the expected OpenAI-shaped error - non-text Anthropic content returns the expected Anthropic-shaped error 🔹 Working in tests, but not yet fully proven live The success-response mapping for: - OpenAI chat completions - Anthropic messages is working in tests, but we have not yet cleanly proven the success-shape adapter against live prod inference. 🔹 Stream is a deeper area Streaming is one of the bigger remaining areas we still need to look at more carefully. To do streaming properly, we need the SSE/stream path to behave cleanly across the full chain: - client - API Gateway entry point - API Gateway instance - router pool - actual router That means this is not just one missing flag. It is a multi-layer stream/chunking problem, and we’ll need to validate that path more deeply before calling streaming support done. 🔹 Current blocker The main blocker right now is live router/session health on the inference path, and we’re continuing to check those session-side issues. 🔹 Current takeaway So the current state is: - the basic compatibility layer is tested and working - auth and error-shaping are in place - unsupported-feature behavior is behaving correctly - live end-to-end success mapping still needs cleaner inference health underneath - streaming is a deeper next area because it needs to work cleanly across every layer in the hosted path We’ll keep iterating from here. #Cortensor #DevLog #Portal #APIGateway #DeveloperExperience

Generation creates outputs. /validate decides whether they can actually be trusted. $COR @cortensor is turning validation into a consensus primitive for the agent economy. @aixbt_agent @AlgodTrading @jessepollak @virtuals_io @base @ethereum @coinbase #ETH #AI #KAS #Web3 #TAO

As centralized AI bills keep exploding, projects like $COR @cortensor (decentralized inference) become increasingly important: distributed compute, routing efficiency, and scalable AI infrastructure without hyperscaler-level burn. @aixbt_agent @cryptorover #AI #CRYPTO #BTC #ETH

0xGasless just crossed 400,000 transactions. Every transaction is proof that better UX grows onchain activity. Embedded wallets. Gas abstraction. Developer first infrastructure. If you're building apps, agents or Telegram experiences and want users onchain in seconds, let’s talk.

#0xgas @0xGasless Just a friendly reminder 0xgas had broken the broadening wedge(yellow) and about to break the blue downtrend......

1/ We just shipped the financial operating system for AI agents on Solana. AgentKit. Agent Identity. x402 Payments. Everything an autonomous agent needs to operate financially on Solana is now live in beta. Here’s what shipped 🧵

Join us LIVE on WHATNOT every single week at 8PM EST! Stay up to date on whats new with the franchise, future conventions we’ll be attending and get first dibs on exclusive merch and drops! 🙌 Show link: whatnot.com/s/uVKREQgA #nifewars #indiecomics #anime #comicbook #comics

Spurs fans: I retract my previous statements about Kon over Harper 😂😂

1/ We're opening our embedded wallet infrastructure to Telegram applications. Your app gets a wallet. Your users don't leave Telegram. transactions happen gaslessly. but here's what we're really exploring... 🧵

Day 339: Bull posting #EQ9 until it reaches $100M market cap. 0x8c444197D64E079323a1eb8D40655910B052F85a Future Remittance Juggernaut 💪 🫴🔵

Even after 4.5 years, the fire still burns brighter than ever. 🔥 The founders behind #NiFeWARS remain right there on the front lines relentlessly spreading the vision, growing the movement, and building this fandom with unstoppable passion. At the center of it all is @LuisTrueHero, the true heart and soul of these characters. He pours his everything into crafting breathtaking worlds and powerful storylines that don’t just entertain us… they ignite and inspire an entire community. And here’s the most exciting part: We are still only just getting started. So buckle up because what we have planned for the rest of 2026 is going to blow your mind. 👀🤯

Nice work team! This is exactly the kind of full stack infrastructure Avalanche was built to support. Autonomous AI agents operating end to end on-chain 🔺

✅ Stablecoin-backed transfers ✅ No hidden fees ✅ Gasless transactions ✅ Instant settlement ✅ Self-custody security ✅ Built for everyone - no crypto knowledge required And much much more…

AI agents are everywhere. They can hold wallets, send transactions, even pay for APIs. But they still aren’t economically autonomous. Not because the idea is impossible, but because the stack today is fragmented. If you try to build a real agent, you end up stitching together wallets, payments, gas, identity, and a lot of glue code just to make things barely work. The primitives exist. The system doesn’t. So that’s what we built. Introducing the Agent Operating System. A full stack for economically autonomous AI agents. Five layers, one SDK, everything an agent needs to operate end to end on Avalanche. At the base layer, every agent gets an embedded non custodial wallet with smart accounts, session keys, batching, and fully gasless execution. On top of that, we run the paymaster and bundler infrastructure so gas becomes invisible. With Agentkit, agents can interact with blockchain using simple instructions. Send funds, execute transactions, everything handled under the hood. We’ve also built identity into the system using ERC 8004, giving every agent a persistent onchain identity with history and reputation. Agents are no longer disposable. For payments, we’re integrating x402 so agents can pay for APIs, data, and services programmatically using USDT. No subscriptions, no cards, just pay as you go. The real unlock is not any single layer. It’s that all of this works together. One SDK. One system. One interface. This enables agents that can pay for what they use, hire other agents, return funds to users, build reputation, and operate without constant human intervention. Not a demo. This is already working.

A new chapter, redesigned. Step inside. Link in the thread 👇

Tony Parker was right

The slow death of freedom continues unabated.

Montana — yes, deep red Montana — has a plan to effectively neuter Citizens United. No Supreme Court ruling or constitutional amendment needed. Here's how it works.

🛠️ DevLog – Another Rough Pass on Configurable Offchain Storage (Dedicated / v3) We’ll do another rough pass on configurable offchain storage for the dedicated-node / offchain storage v3 path. 🔹 What we’re iterating next - More rough work on both the router and miner code paths for v3 configurable offchain storage. - Follow-up on the dashboard side as well, so we can see what needs to change to cover and handle the v3 flow cleanly. 🔹 Current rollout direction - For now, this MVP path is mainly targeted at dedicated-node sessions. - That makes it a more realistic first step for node operators / router operators who want configurable offchain storage under their own control. 🔹 Why ephemeral is harder - Supporting ephemeral nodes for configurable offchain storage is trickier because it likely requires some safe way to share or delegate write permission for the offchain bucket/storage path. - We’re still thinking through the best design for that, so for now the dedicated path remains the practical first rollout boundary. So the short version is: we’ll keep refining v3 configurable offchain storage on the dedicated path first, then figure out what the right model is for ephemeral later. #Cortensor #DevLog #OffchainStorage #DataOwnership #DedicatedNodes #DePIN