@matei_zaharia: Really excited to open source a new project: Omnigent, a meta-harness for AI agents. It lets you build multi-agent codi…
Summary
Matei Zaharia announced the open source release of Omnigent, a meta-harness for AI agents that enables building multi-agent coding and custom agents by composing tools like Claude Code, Codex, and Pi, with added live collaboration and control policies.
View Cached Full Text
Cached at: 06/13/26, 06:24 PM
Really excited to open source a new project: Omnigent, a meta-harness for AI agents.
It lets you build multi-agent coding and custom agents, sitting above Claude Code, Codex, Pi, and agent SDKs to let you compose them. It also adds live collaboration and rich control policies. https://t.co/jwFmH8nHsZ
Similar Articles
Tiny Basic for Arduino
Tiny Basic for Arduino is a lightweight, portable BASIC interpreter for mid-range Arduino boards and MCUs, featuring an in-hardware code editor and a comprehensive built-in standard library for hardware I/O, math, and bit manipulation.
Octomind – open-source AI harness that saves your tokens, static rust
Octomind is an open-source, Rust-based CLI-first AI coding agent runtime that gives LLMs access to repos through MCP tools, supporting interactive, piped, daemon, WebSocket, and ACP sub-agent modes with TOML-based guardrails, budgets, and adaptive compression.
mtmd : add Nemotron 3.5 Transcribe support by pskrunner14 · Pull Request #31471 · ggml-org/llama.cpp
A pull request to llama.cpp adds Nemotron 3.5 Transcribe support in the mtmd (multimodal) module, extending the library's audio transcription capabilities.
@Saccc_c: Inspired by the legendary Karpathy’s HackerTube, I built a website called “AnliBili” that brings together high-quality Bilibili videos repeatedly recommended on social media over the past 16 years, helping you cut through the noise! By organizing and categorizing nearly 10 million discussions on Zhihu and Xiaohongshu spanning 16 years, I selected 1,132…
Inspired by Karpathy’s HackerTube, the author used Teamily AI’s multi-agent workflow to build “AnliBili,” a website that curates 1,132 high-quality Bilibili videos repeatedly recommended across nearly 10 million discussions spanning 16 years on Zhihu and Xiaohongshu, helping users cut through information noise.
Stealth "Pulse Alpha" on VoldemortCode, appears to use GLM tokeniser - GLM 5.5 perhaps?
OpenCode has launched a mysterious stealth model, Pulse Alpha, offering 1M context, 131K max output, multimodal input, and three reasoning tiers — free for a limited time. Speculation points to GLM 5.5 or the Qwen series under the hood.