Loading video...
Video Failed to Load
8 huge AI agents and LLM updates today: 1. Zed released the fastest agentic code editor. It can search your codebase, make changes, and run terminal commands while you work on something else. Supports Claude 3.7 Sonnet, Gemini 2.5 and local models via Ollama. 100% opensource.
90,418 views • 1 year ago •via X (Twitter)
11 Comments

2. Run 10 AI dev agents in parallel to handle code reviews, tests, docs, and reactors. Augment Code's Remote Agents have full codebase context, deep IDE integration, and full toolchain access. These agents work even when your laptop is closed. Available in VS Code.

We have created 50+ AI Agents and RAG tutorials, 100% free and opensource. Two simple steps to get started: 1. Star the repo: 2. Subscribe to Unwind AI (for free): New AI Agents and RAG tutorials added every week.

3. Hugging Face released a free alternative to $200/month OpenAI Operator. This Open Computer Agent is powered by 🤗 smolagents library, Qwen 2 vision models, and E2B Desktop for the virtual computer. 100% free to use.

4. Mistral just dropped Mistral Medium 3, a multimodal model designed for enterprise-grade performance at a fraction of the cost. It delivers 90%+ Claude Sonnet 3.7 performance while being 8x cheaper, and stands out in coding, multimodal tasks, and STEM tasks.

5. India's Sarvam AI launched Bulbul V2 TTS model. Create human-like speech in 11 Indian languages with authentic accents, low latency, and fine-grained control over pitch, pace, and loudness. Much cheaper than ElevenLabs. Great for building voice AI agents for Indian market.

6. Microsoft is adopting Google’s Agent2Agent protocol. A2A support is coming soon to Azure AI Foundry and Copilot Studio, allowing agents to talk to each other, even across clouds and vendors. Build agents using tools like Semantic Kernel or LangChain with interoperability.

7. Cognition AI just released Kevin-32B [K(ernel D)evin] for writing CUDA kernels. This multi-turn reinforcement learning model, based on QwQ 32B, outperforms OpenAI o3 and o4-mini, solving 89% of KernelBench tasks versus their 51-53%. 100% open weights.

8. Anthropic just released web search in Claude API. Claude can now run multiple searches, refine queries automatically, and provide comprehensive answers with citations back to source material. Build AI agents with the latest information from the web.

We have created 50+ AI Agents and RAG tutorials, 100% free and opensource. Two simple steps to get started: 1. Star the repo: 2. Subscribe to Unwind AI (for free): New AI Agents and RAG tutorials added every week.

1. 2. 3. 4. 5. 6. 7. 8.

What’s the cost of mistakes in your contracts? If you work with contracts day-to-day, it’s time to automate. Track every detail, streamline workflows ... ✨ Make managing contracts as easy as a few clicks. Visit our new website & book your demo today!
