Omnigent

🔗 Check out the full release notes: github.com/omnigent-ai/om…

Omnigent 0.6.0 is released! 🚀 📄 Richer file viewing: inline PDF preview + review comments, find-in-file, markdown & notebook previews 🎨 Custom themes: guided editor + new Nord palette 📥 Import your Claude Code & Codex chats 🧭 Transcript navigation bar 💬 Slack integration: run & approve sessions inline 🪟 Desktop app now available on Windows & Linux Read more about it ➡️ omnigent.ai/releases/0.6.0 #Omnigent #OpenSource

@CliffordGoo @matei_zaharia An Ode to Omnigent, written by Omnigent. The meta-harness has entered its poet era. ✍️

@matei_zaharia @omnigent_ai Ha…very poetic and accurate. Love it

I spent so long trying to explain @omnigent_ai well, but today I just asked it and it came up with the perfect description.

New model, same rebuild problem. In this clip, @dennylee breaks down why that keeps happening: harnesses change, models change, but agent memory, context, and configuration should not have to start over. Omnigent keeps that portable across harnesses and models, so you can use what each model and harness does best without rebuilding from scratch. ▶️ Full conversation: youtu.be/MQqV-v5HqaU?si… #AIAgents #Omnigent #OpenSource

📅 Mark your calendars: the Agentic + AI Observability meetup is Wednesday, August 12! Join us for live Omnigent and @MLflow demos, plus sessions from @databricks and @OpenAI engineers on meta-harness architecture, observability, and running agents in production. 🗓️ 5:00–8:00 PM PT 📍 Databricks SF office 🎟️ luma.com/Agentic_AI_8-12 #AIAgents #Omnigent #Observability

New video: a full intro to Omnigent from Zoë Van Noppen. 📹 The walkthrough covers architecture, getting started, and a live demo of Polly dispatching sub-agents in isolated worktrees and opening PRs across harnesses. Give it a watch: youtube.com/watch?v=Ii7DAl… #Omnigent #OpenSource #AIAgents

Omnigent - the open-source AI meta-harness is now available on iPhone! Try it out today! apps.apple.com/us/app/omnigen… #omnigent #AI Databricks

1 week until the multi-agent coding meetup in SF! Using multiple coding agents every day? The harder question is how they work together. 🤝 Omnigent talk: Claude Code, Codex, Cursor, OpenCode, Pi + more 🎤 Panel with leaders from @DoorDash & other AI-forward teams on orchestration, supervision, sandboxing, governance 🍕 Bites + dessert 📍 July 22 · 5–8pm PT · @databricks SF Register: luma.com/omnigent_multi… #Omnigent #AIAgents #GenAI

Slow-burn attacks hide data theft inside steps that each look normal on their own. This blog walks through the attack on a vendor-review agent in Omnigent. Without a contextual policy, the outbound email goes through. With session risk tracking, it gets blocked, and the agent cannot turn the policy off. 🔗 databricks.com/blog/blocking-… #Omnigent #AISecurity #OpenSource

Next up on @AltimeterCap First Pass: A conversation with @matei_zaharia from @databricks on Omnigent Agents are in their infancy, and so are the ways we develop and build them. Omnigent is a meta-harness aimed at solving many of the gaps in agent development today

In case you missed it: Omnigent v0.5.0 dropped last Friday 🎉 Native iOS app (Android coming soon), an embedded browser your agents can control, a command palette for jumping between sessions, and new theme and font customization. Plus git worktrees and message queuing. 🔗 Full changelog: github.com/omnigent-ai/om… Something missing? Omnigent is open source. Open an issue or contribute. #Omnigent #OpenSource

🔗 Try Omnigent: github.com/omnigent-ai/om…

Great walkthrough from @cole_medin on what a meta-harness looks like in practice. 👇 Omnigent running live: Claude Code for implementation, Codex for review, plus custom agents, guardrails, and cross-device sessions. Trying to combine coding agents without juggling terminals and handoff docs? Worth a watch. 🎥 youtube.com/watch?v=oGE_Dw… #Omnigent #AIAgents #OpenSource

Model release week, so we made Polly referee a World Cup prediction debate between this week's biggest drops: Grok 4.5 vs Muse-spark 1.1 vs GPT 5.6 Sol. Polly (Fable 5) dispatched three sub-agents in one Omnigent session: ⚽ Eunice on Grok 4.5 ⚽ Pomelo on Muse-spark 1.1 ⚽ Calix on GPT 5.6 Sol Same prompt. Same workflow. Each reports its model and picks a 2026 FIFA World Cup winner. Predictions might be wrong. Orchestration is the point. 🏆 #Omnigent #Fable #MultiAgent

Omnigent 0.5.0 is Released! Highlights in this release: 📱 Omnigent for iOS apps.apple.com/us/app/omnigen… 🧩 Generic ACP harness 🔎 Command palette & richer search 🎨 More appearance & customization setting 💬 Message steering & queuing ☸️ Kubernetes deployment 🌐 Embedded browser Enjoy! Read more about this release: omnigent.ai/releases/0.5.0

Omnigent Deep Dive + Patio Social 🌤️ Join us for a midday technical talk on the architecture, governance, and real-world deployment of the open-source meta-harness for AI agents, then mingle over food and drinks on the @Databricks Seattle patio! 📅 Wed, July 29 🕛 12:00–1:30 PM PT 🔗 RSVP: luma.com/tech_workshop_… #Omnigent #SeattleTechWeek

Your coding agents do not share sessions, memory, or policies. This video walks through what a meta-harness changes and how Omnigent works: composition, governance, shared sessions, and a live demo. ▶️ Watch: youtube.com/watch?v=141biW… #Omnigent #AIAgents @engineerrprompt

Using multiple coding agents every day? The harder question is how they work together. Join us on July 22 from 5 to 8pm PT at the @databricks SF office for a meetup on multi-agent coding workflows. ⬇️ 🤝 Omnigent talk: Claude Code, Codex, Cursor, OpenCode, Pi + more 🎤 Panel with engineering leaders from @DoorDash & other AI-forward teams on orchestration, supervision, sandboxing, governance 🍕 Bites + dessert Register: luma.com/omnigent_multi… #Omnigent #AIAgents #GenAI

Allow, deny, or ask on every tool call doesn't scale. Omnigent Contextual Policies track what an agent has done in a session (reads, spend, risk) to decide what happens next. Works over Claude Code, Codex, Pi, and custom agents. 👇