Nous Research’s open-source Hermes Agent now ships a non-blocking async_delegation toolset, tracked in GitHub issue #5586. The existing delegate_task, which froze the parent chat until all child subagents finished, is supplemented with asynchronous tools: delegate_task_async returns a task_id immediately, while check_task, steer_task, collect_task, cancel_task, and list_task manage the background run. Subagents remain strictly isolated—each gets a fresh conversation and only a final summary returns to the parent, preserving context windows. Background agents execute as in‑process threads using the same AIAgent machinery, model routing, and credential pool; users enable the update with `hermes update`.
The team behind the open-source MetaGPT framework has launched Atoms, a vibe coding platform that uses a team of AI agents to handle the entire product lifecycle. Agents include Iris (deep researcher), Emma (product manager), Bob (architect), Alex (engineer), Sarah (SEO specialist), Adrian (ads specialist), David (data analyst), and Mike (team leader), coordinating research, scoping, full-stack development, deployment, SEO, and Google Ads management. Every app comes with Atoms Cloud providing built-in authentication, real-time database, Stripe payments, scalable hosting, and one-click deployment. A Race Mode runs prompts across multiple frontier models to improve accuracy up to 3×, and users retain full code ownership with export to GitHub. Atoms offers a free tier with 15 credits per day and Pro plans starting at $20/month, differentiating itself from Lovable and Base44 by bundling market research and distribution tools into the build workflow.
Google Cloud announced Open Knowledge Format (OKF) v0.1, an open, vendor-neutral specification that formalizes the LLM-wiki pattern as a portable directory of markdown files with YAML frontmatter. OKF is not a service or platform—it requires no SDK, runtime, or registry—and a bundle renders on GitHub, ships as a tarball, or mounts on any filesystem. Each concept is one markdown file identified by its path, with only one required field (type) in the frontmatter; cross-links between files form a knowledge graph that agents can navigate without translation. Google released reference tools including a BigQuery enrichment agent, a static HTML visualizer, and sample bundles. The format targets the scattered internal knowledge problem, letting agents consume curated, version-controlled context directly, unlike retrieval-augmented generation (RAG).
Databricks released Omnigent, an Apache 2.0-licensed open-source meta-harness that standardizes the interface across terminal coding agents (Claude Code, Codex, Pi) and agent SDKs, turning them into interchangeable components. It adds a shared layer for composition (switching agents with one-line changes), contextual control (e.g., pausing at cost limits, requiring human approval for sensitive git pushes), and collaboration (sharing live agent sessions via URL). The architecture consists of a sandboxed runner with a uniform API and a policy server, and sessions sync across terminal, web UI, and mobile. An OS sandbox (Omnibox) secures credentials by injecting tokens only in approved proxy requests. Two example agents—Polly (a multi-agent coding orchestrator) and Debby (a two-headed brainstorming partner)—illustrate its patterns, and an interactive concept demo shows parallel agent delegation and policy enforcement.
This tutorial demonstrates a complete QwenPaw agent workspace setup in Google Colab. It covers installation, environment configuration, and authentication with a randomly generated password. The setup automatically configures an LLM provider from Colab secrets (OpenAI, OpenRouter, DashScope, DeepSeek, or Gemini) and creates a custom research_brief skill along with demo knowledge files. The QwenPaw Console is launched on a configurable port, made accessible via Colab proxy and optionally a Cloudflare tunnel, and a streaming chat API client is used to test the agent's responses. The result is a reproducible, secure, and extensible local-first agent platform for research and automation workflows.
Moonshot AI released Kimi K2.7-Code, an open-weight, coding-specialized agentic model under Modified MIT license. It is a Mixture-of-Experts architecture with 1T total parameters, 32B active per token, 384 experts with 8 selected, MLA attention, SwiGLU feed-forward, and a 400M-parameter MoonViT vision encoder. The model supports a 256K-token context window, ships with native INT4 quantization, and enforces mandatory thinking mode with fixed sampling parameters (temperature 1.0, top_p 0.95, n 1). In company-reported benchmarks, K2.7-Code achieves 62.0 on Kimi Code Bench v2 (+21.8% over K2.6), 81.1 on MCP Mark Verified (beating Claude Opus 4.8’s 76.4), and demonstrates approximately 30% lower reasoning-token usage than K2.6, reducing cost and latency in agentic workflows. The 595 GB model weights are available on Hugging Face and can be self-hosted via vLLM, SGLang, or KTransformers; API access uses the kimi-k2.7-code model name with OpenAI-compatible endpoints.