SOMEONE OPEN SOURCED A SMALL MODEL TRAINED SPECIFICALLY AS... A PERSONAL AGENT ROUTER DECIDES WHAT RUNS LOCAL VS CLOUD AUTOMATICALLY ROUTES TASKS TO THE RIGHT MODEL BASED ON COMPLEXITY SMARTER AGENT ORCHESTRATION WITHOUT THE OVERHEADshow 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

Funny how you can do the same thing with... a local model without sending all your data to a remote cloud.show more

Claude Code's new dynamic workflow is the real deal.... 🤖 Why it matters: It's not just a chain of prompts — it's an autonomous agent swarm. 1. Set model to Opus 4.8 + reasoning effort /ultracode 2. Claude detects complexity, writes orchestration script on the fly 3. Spawns a parallel fleet of coordinated subagents Operator takeaway: This is the first time I've seen an agent actually decompose and delegate autonomously without a rigid framework. Have you tried it yet? 🚀show more

What if your model handled its own tuning? ⚙️... With NVIDIA TAO 7, just prompt your coding agent what you want in plain language and let it do the rest. • Agent skills plug into your coding agent and improve accuracy. • AutoML removes the guesswork from hyperparameters. LLM-guided tuning finds strong configs up to 2x faster. • Fine-tune any Hugging Face CV or VLM model on local NVIDIA GPUs. • Data enhanced fine-tuning helps your agent identify why the model fails, then fix it. Try TAO skills ➡️show more

Turn your Cursor agent window into a deck builder.... Composer 2.5 + open-slide is a great combo - the model handles design and generation cleanly, and the browser integration lets you watch the deck come together live as the agent works. $ 𝚗𝚙𝚡 @𝚘𝚙𝚎𝚗-𝚜𝚕𝚒𝚍𝚎/𝚌𝚕𝚒 𝚒𝚗𝚒𝚝show more

Let me explain the agent loop, simple It's the... core of every agentic system, and the part most people overcomplicate It's just this: 1. Send messages to the model 2. Model responds, maybe calls a tool 3. You run the tool 4. Append the result back to messages 5. Repeat until stop_reason is end_turn Step 4 is the whole thing, the write-back is what makes it an agent The model has to see what actually happened before it decides the next move That's the entire loop... understand this cold before you reach for a frameworkshow more

We're excited to power LemonSlice's new video agent product.... Turn your real-time voice agent into a video agent using a single photo. The underlying model—which autoscales on Modal 😉—streams infinite-length talking video at 20fps using a single GPU.show more

let me save you 3 hours of head scratching.... if you're running local models like Qwen3.5-35B-A3B through Claude Code via llama.cpp's Anthropic endpoint, the chain will break every 3 to 5 minutes. tool call fails. flow stops. you reprompt. it recovers. 2 minutes later it stops again. the model is fine. the harness chokes on local inference latency. switch to OpenCode. same localhost endpoint. same model. same GPU. the chain doesn't break. the tradeoff: OpenCode sometimes loops. the model forgets what it already read and repeats the same tool call. but a loop you can interrupt. a broken chain kills your momentum and you start over. watch both side by side. proprietary agent vs open source agent. same 3B model. different failure modes. pick your poison.show more

Stop spending hours on manual work. You can now... use a multi-agent AI workforce to get more work done in less time. Here's how 👇 --- Try Eigent AI - Lets you build and run a custom AI workforce on your desktop. - Automate complex workflows using multi-agent task execution. - Built on CAMEL-AI’s top open-source projects ( CAMEL-AI.org & OWL). - Boost productivity with deep customization and strong privacy --- Features: - Customize Your AI Workforce: Build task-specific agents with domain skills and tools. - Faster Execution: Eigent runs agents in parallel to automate complex workflows. - Human-in-the-loop: Automatically asks for help when tasks hit uncertainty. --- What sets Eigent apart? - 3–5× faster task execution using a parallel multi-agent workforce. - Modular design lets you add new capabilities without changing the core system. - Self-optimizing agents that replan and adapt during execution for higher success. - Deploy anywhere: cloud, local, or enterprise, with full open-source flexibility. --- Try building your multi-agent AI workforce here: Join their community to build your multi-agent workforce: Check their GitHub: ---show more

i found a way to make UNCENSORED AI AGENT... on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have funshow more

Open weight models are now available in Kiro. Three... open weight models are available in the IDE and CLI, so you don’t have to default to the largest model for every task. Choose the right model based on speed, cost, or long-running agentic workflows. What model would you like to see supported next? #Kiro #BuildwithKiro #AICodingshow more

i just open-sourced one of our internal GTM skills... introducing the /company-research skill ask your agent to build you a target account list - it finds prospects that fit your ICP and runs deep research on every company via the Browserbase CLIshow more

Gemma 4 looks at a parking lot. Decides what... to ask. Calls SAM 3.1. "Segment all vehicles." 64 found. "Now just the white ones." 23 found. One model reasoning and orchestrating. One model executing. Both running locally on a MacBook. MLX. No cloud. No API.show more

Fable 5 + Higgsfield MCP = a full marketing... team inside Claude. The most anticipated model in AI runs content pipelines and deep analysis. With /goal, /loop, and a Fable 5 agent council, agent-run marketing is about to take off. A month of campaign work ships in a day.show more

Most people see a Mac Mini as a home... computer. He saw a $300 invoice waiting to happen. A guy in Shenzhen figured out that every early-stage startup, every founder, every small business owner needs the same thing, someone to tell them what their competitors are doing and where the gaps are. Nobody wants to pay $2,000 for a research firm. Nobody wants to wait a week. He set up Hermes on a laptop. Local model. No API costs. First report took 15 minutes. He charged $300 and delivered same day. Then he bought another machine. Then another. Now there are 65 Mac Minis on metal shelves in his apartment. Each one runs its own agent. Each agent has its own skills folder that grows every time it completes a task. Month one: $3,200. Month three: $9,600. The tool: Hermes Agent. Free on GitHub. The model: Qwen 3.6 27B. Also free. Total monthly cost: $2 in electricity. The hardware paid for itself in week two. The shelves haven't changed. He just keeps adding machines.show more

You don't need a more expensive model. You need... better reasoning. Every frontier LLM got smarter with SERV: - smaller ones match frontier performance - frontier ones go past what they were built for The question isn't which model to choose - it's what engine it runs on.show more

Don't train the model, evolve the harness. I read... a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.show more

Helmor has been out as an open-source coding agent... orchestrator for less than a week, and we’re already close to 1,000 GitHub stars!!! As a little gift, we shipped a new feature you’re going to love. 👇 Stop copy-pasting GitHub links, Linear tickets, Slack threads, and random notes into prompts. We're tired of rebuilding context every time I ask an agent to do work. Contexts in Helmor is another step toward a local dev loop: browse, preview, inject context, and dispatch tasks without leaving the app. Before you start a task, Helmor should help you gather the right context first. Try the open-source Helmor — link in the comments. #Helmorshow more