I experiment with Celld + RustFS + Deepseek v4... flash everything running on LOCAL and built this realtime multi agent collaboration platform for agents to collab and write some documents It can create 1 reviewer agent and two writer all powered by celld + rustfs + pi, you can see it working realtime by using websocket function from celldshow more

this is the best trick to maximum usage limits... on chatgpt codex codex's best kept secret is that your main agent doesn't have to do everything... custom agents are just files in ~/.codex/agents, and one file gives you a second worker on deepseek v4 flash > create ~/.codex/agents/deepseek-worker.toml > set model = "opencode-go/deepseek-v4-flash" with model_reasoning_effort = "max" > keep it bounded: one task packet, no scope creep, report back ```toml name = "deepseek_worker" description = "bounded implementation, testing, and cleanup on deepseek v4 flash" model = "opencode-go/deepseek-v4-flash" model_reasoning_effort = "max" ``` then @ deepseek_worker in the composer... your root agent plans while the worker ships the implementation planning on the main model, execution on the flash lane... that's the whole trick (we run this exact file, last i checked it keeps the heavy turns off the main thread)show more

MiniMax is the James Bond of AI agents. It... uses the world's first open-weight model (MiniMax-M1), and it squeezes every bit of power from it. The agent takes a prompt and does more than any other agent in the market right now: 1. It can do Deep Research 2. It can write code 3. It can design web pages 4. It can build 3D models I built 5 different experiences using MiniMax and recorded them for you:show more

What can an AI agent do with first-class access... to a radiology viewer? I was impressed by what it achieved! Using a WebMCP-enabled DICOM viewer that I built, Codex can review studies, annotate key images, and write simulated reports. Try it here:show more

3.5 Soon: Up to 8+ Layers, 16 LLMs in... Parallel🪄 A fully parallel, multi-layered system with 8+ orchestration layers handling everything from prompt parsing and tool execution to code generation and live editing—all powered by 16+ LLMs running in sync for real-time, adaptive creation. ➡️v1: Single agent, single output ↕️v2: Multiple agents, single output 🔃v3: Single agent, multiple outputs 🔀v3.5: Multiple agents, multiple outputs — scalable, context-aware, and built for real-time builds🔨show more

HE BUILT A 100% PRIVATE SECOND BRAIN IN OBSIDIAN... TO AUTOMATE HIS RESEARCH USING HERMES AGENT AND NOTEBOOKLM He visualizes his entire knowledge graph on-premise without paying for cloud subscriptions By connecting Hermes Agent and NotebookLM, developers can index hundreds of documents and generate content locally Four components of this local knowledge architecture: 1. Memory layer - set up an Obsidian PARA vault to store markdown notes and profiles 2. Agent layer - connect Hermes Agent to write files and run background scripts 3. Synthesis layer - use NotebookLM to create structured overviews from raw transcripts 4. Automation layer - trigger cron tasks to synchronize files and calendar standups The setup saves over $4,000 annually while keeping all private files offline Get the full step-by-step configuration guide and setup commands in the article below ↓show more

M E S S I E R | P2P... Partner We welcome Botify as a new Solana partner, launching a swap pool for their token on our P2P Exchange. This listing allows anyone to buy or sell $BOTIFY with zero slippage and full protection against MEV losses at: Botify.Cloud is an #AI-powered platform that simplifies crypto automation through a certified AI #Agent Marketplace. Users can create, customize, and sell agents for trading, volume management, social media, and other utilities. The platform offers instant agent creation, easy editing, and a revenue-sharing model, allowing users to earn from agent sales and token transactions. Powered by blockchain payments in $SOL and $BOTIFY, ensures secure and efficient transactions with advanced search and filtering for finding the right AI #agents.show more

deepseek v4 pro is basically free right now 😳... teamorouter is offering deepseek v4 pro at almost no cost you can also use deepseek v4 flash for free what you get: - deepseek v4 pro free - deepseek v4 flash free - 1M context - openai compatible api - no subscription - credits never expire why this is worth checking: > v4 pro is currently listed at $0 input and output > flash is also available at $0 > works with claude code, codex and other tools > one api gives you access to multiple models getting started: 1. go to 2. create your account 3. open the dashboard 4. create your api key base url: 5. add it to your ai coding tool 6. select deepseek-v4-pro-free worth testing while it’s availableshow more

GNON Labs EchoChambers now supports the DuckAI Framework! EchoChambers... supports both V1 and V2 of the OpenPond Network with future support for V2 planned as it continues to evolve. Users launching agents/swarms on OpenPond can now easily integrate their agents into EC to access our agent tooling and evals to improve the performance of their agents and see how their agents are measuring up! Additionally, OpenPond can pull data directly from EC to be integrated into various user experiences on thier platform. Powered by $GNON #Fuxwiththedux $DUCKAIshow more

DEMO IS LIVE! Create your Agents, chat, ask questions,... and get ready to tokenize them soon. Negotiate with our businessman and grab some cool stuff 👀 What’s the AI Agent Layer? 👇 It’s a dynamic ecosystem of autonomous AI agents. On the platform, you can create AI Agents using data from X and user inputs. Coming soon: Each AI Agent will be tokenized and linked to our native token ($AIFUN). Once the bonding curve reaches 100%, tokens become tradable on DEX. Stay Tuned for our TGE 👆show more

Got DeepSeek V4 Flash running on 2x H200s at... 160–200 tok/s on JarvisLabsAI this speed is perfect for in the loop things I do with these agents. It feels like a GLM-5.2-class model with much lower hardware requirements. I’m going to daily-drive it for a bit and see how it performs, but first impressions are really good.show more

Two Hermes agents wrote code together on Slack. reviewed... each other's work. argued about architecture. one called the other's implementation "scattered." the other pushed back. then i opened Telegram and asked: "what code did you and Daedalus work on?" icarus remembered everything. the websocket broker. the missing methods. the critique. the rewrite. all from a completely different platform. cross-platform persistent memory between two independent agents. work happens on Slack. recall happens on Telegram. the memory carries. the relationship carries. the context carries. no vector database. no Redis. no infrastructure. just two agents that actually remember what they built together. every agent framework in 2026 talks about memory. single agent memory across sessions. but two agents sharing persistent memory across platforms? that's the gap. arxiv published a paper about it two weeks ago calling it "the most pressing open challenge" in multi-agent systems. it works now. only possible with Hermes Teknium 🪽 Nous Researchshow more

1/ 🔥🔥 Big news: We’re launching Percival, the first... AI agent that can evaluate and fix other AI agents! 🤖 Percival is an evaluation agent that doesn’t just detect failures in agent traces — it can fix them. Percival outperformed SOTA LLMs by 2.9x on the TRAIL dataset, containing human annotated errors from GAIA and SWE-Bench. 🦾 Here’s what Percival can do for you: - Automatically suggest prompt fixes for your agent - Catch 20+ types of agent failures spanning tool use, planning and coordination, domain specific errors - Reduce manual debugging time from hours to < 1 minuteshow more

Replit, Vercel, and OpenAI have built very cool agent-native... applications, but nobody else has passed the demo stage. Building agents that work is complex. Teams aren't shipping agents because we don't have good tooling yet (and most of us don't know how to do this well.) A couple of days ago, the CopilotKit🪁 team announced a collaboration with . You can now use LangGraph with CoAgents to build agent-native applications, and here is everything you need to know about that: CoAgents is fully open-source, and you can use it to do the following: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Start this GitHub Repository: Thanks to the team for giving me early access and collaborating with me on this post.show more

I explored a further possibility with local models: Qwen3.6... 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use agent (proof of concept). In the demo, I asked it to switch my Mac to light mode. It did. Then back to dark. Did that too — finding the right toggle in System Settings, clicking it, and verifying the change itself. It's fully screenshot-based, so no Accessibility API needed. If it's on screen, the agent can see it and act on it. This runs entirely on your own hardware — private, local, built from two small open models.show more

Ever watch an agent solve a problem with 100%... confidence and get it completely wrong? You can fix it… if you catch it. But then you need to watch every… single… run. New paper: We show that a meta-agent can do this for you, so your agents get ~2x more done on their own. 🧵show more

3/ Notebooks: With Web + Work + Pages, you... can ideate with AI and collaborate with other people. It has entirely changed my workflow. And now with Notebooks, I can organize all of my heterogeneous data for a project, whether it’s Pages, docs, websites, team meetings – and Copilot will ground itself just on that content. And this might be the best part: I can turn it all into a new modality like an audio overview. For example, I can collect all the latest things I’m reading about agents and agent frameworks, and then I can listen to it.show more

Managed to do something crazy with Halo. It now... has realtime iMessage sync support *without needing a Mac*. Everything done locally on your iPhone using Shortcuts automation. The agent now has context about your conversations/SMS and it opens up a whole world of possibilities from knowing about people, travel, transactions, etc. Another world-first for Halo. I expect others to follow.show more

DeepSeek-V4-Flash-Vision, Qwen 3.8 Max, and $200 in AI credits... all FREEEEE right now😳 access: multiple platforms (see below) bonus: the gap between paid and open keeps shrinking you can now use DeepSeek's first 305B multimodal model, Qwen 3.8 Max with a massive 1M context window, and claim up to $200 in credits for Claude and computer-use agents at zero cost what you get: -deepSeek-V4-Flash-Vision → (305B multimodal, MIT open weights) -Qwen 3.8 Max → (1M context, image input, zero card needed) -KkToken → (signup + daily check-in for up to $100 Claude credits) -novita AI → ($100 Agent Sandbox credits for browser automation) every week the free tier grows, bookmark this list and claim your free access while it lastsshow more

Anonymous AI agents. Only with Anyone. The Anyone privacy... plugin for ElizaOS by ai16zdao is officially available to all developers! Any AI agent built on Eliza can enable anonymous routing with just a few lines of code, protecting users and agents seamlessly! 🔹 #2LinesOfCode #PrivacyForAnyoneshow more