Omnigent
@omnigent_ai
A meta-harness for AI agents - more info at
0 Following 1K Followers
Omnigent makes it easier to work across GitHub repositories. 👇
🔀 Track multiple GitHub PRs in one session, including from different repos
📄 Switch between PR summaries and diffs; manually link or unlink PRs
📦 Multi-repo sandbox: choose repos and branches at session create; cloned in parallel for the agent
Learn more:
#Omnigent# #GitHub#
Show more
The latest @omnigent_ai release added support for more sandboxes and databases. Use your preferred harnesses, managed sandboxes, models, and databases on Omnigent.
#AI# #Metaharness#
Show more
We did it! Omnigent has officially surpassed 10,000 GitHub stars ⭐
Thank you to everyone who starred the repo, filed issues, shipped PRs, and ran agents with Omnigent. Here's to the next 10k! 🚀
Come build with us:
Join the community on Discord:
#Omnigent# #OpenSource# #AIAgents#
Show more
The new @omnigent_ai compose makes it super easy to configure your sessions in one place. workspace, agent, model, reasoning effort, and permission controls are now all in the same place, ready when and where you need them.
Show more
Today I needed to share some context from one chat to another in @omnigent_ai . I found that you can just copy the session ID into the new chat, and your agent can pull what it needs from the chat history. Convenient!
Show more
Omnigent v0.14.0 is now available! 🎉
This release makes it easier to work across GitHub repositories, configure sessions, and keep track of ongoing work.
🔀 Multi-repo GitHub PRs and sandboxes
🎛️ Redesigned composer
🪟 Claude SDK /compact
🗄️ Gensee, Kubernetes, CockroachDB
🔁 Approvals that survive restarts
Learn more 👉
#Omnigent# #AIAgents# #OpenSource#
Show more
New video: @leonvz demos Omnigent running Claude Code and Codex in one open source meta-harness.
He plans a 3D game, forks into Debby for a multi-model debate, then hands off to Polly to delegate the build. Policies, MCP, and prompt injection guardrails too. 👇
🎥 Watch:
#Omnigent# #AIAgents# #OpenSource#
Show more
A new GitHub panel in the session workspace rail shows the branch's pull request without leaving Omnigent. 👇
📋 Summary, comments, CI checks
🗂️ Stacked diff with a file-tree navigator
🔄 All refreshing live as the agent pushes
Start a New Chat from a repository with an open pull request, then open the panel and switch between the split Summary and Changes tabs.
Learn more:
#Omnigent# #GitHub#
Show more
2 weeks until Open Lakehouse + AI Meetup in Paris 🇫🇷
Building with MLflow? Don't miss @omnigent_ai: A Meta Harness for AI Agents. Aravind Segu and Edwin He will show how to capture @opentelemetry traces for observability in MLflow across multi-harness agent workflows.
🗓️ Sept 23 | 6–9:30 PM CEST
📍 La Fondation
👉 RSVP:
#MLflow# #AIAgents# #Paris#
Show more
Omnigent 0.13.0 is here with faster and more responsive sessions, UI enhancements including a new GitHub panel and Canvas view, and new sandboxes and harnesses.
Note that managed terminals now require tmux 3.3 or newer. @omnigent_ai will warn you if you need to upgrade.
#AI#
Show more
Omnigent v0.13.0 is now available! 🎉
This release is focused on tightening the loop between your agents, your code, and the infrastructure they run on.
🔀 GitHub PR panel in the session workspace
🖼️ Built-in Canvas board of live session cards
📦 New managed sandboxes: libkrun microVMs and self-reclaiming Kubernetes
⚡ Instant session switching
🔌 Jcode as a first-class ACP harness
Full release notes 👉
#Omnigent# #AIAgents# #OpenSource#
Show more
A workflow can move from Cursor to Claude Code to Pi to Codex by copy-pasting prompts and outputs. Each harness logs differently, which leaves a hole when you try to debug, audit, or trust the run.👇
This blog shows how @omnigent_ai unifies that interface and sends standardized traces to MLflow: agent turns, tool calls, per-turn tokens, and session metadata, with no app code changes.
🔗
#MLflow# #Omnigent#
Show more
LLM bills spiral when debugging sessions or multi-agent workflows run away. Omnigent warns first, then downgrades, doesn't hard-stop mid-task. 👇
🛡️ trivial_gate routes trivial requests off Opus, Fable, GPT-5
💰 Progressive budgets block expensive tiers; work continues on Sonnet/Haiku
📊 /usage breaks spend by harness, model, and session
Phased rollout: visibility → routing → budgets
Read more:
#Omnigent# #LLMOps# #GenAI#
Show more
Omnigent v0.12.0 is now available! 🎉
This release is focused on meeting your existing tools and workflows where they already live.
📥 Import Claude Code, Codex, and other CLI sessions into the web UI
📁 Projects now drive new sessions
📱 Refreshed mobile and wide-screen UI
🔌 Antigravity, plus Devin and Grok Build in the New Chat picker
🖥️ Run your host as a service on macOS and Linux
Full release notes 👉
#Omnigent# #AIAgents# #OpenSource#
Show more
Check out this hands-on walkthrough of Omnigent from Daniel Beach: what a meta-harness actually is, without assuming you already live in this stack.
The blog covers installing Omnigent, connecting Claude Code and Copilot, and the pieces that matter in daily work.
🔹 One common layer over your coding harnesses, plus a Web UI next to the terminal
🔹 Policies for cost and safety, including asking before git and bash
🔹 Polly for multi-agent planning and research
👉 Read the full post:
#Omnigent# #AIAgents#
Show more
📣 Hey Paris: Join us on Sept 23 for the next Open Lakehouse + AI meetup!
Aravind Segu and Edwin He will cover why to use a meta-harness: collaborate on your work, exercise control, and choose your coding agent harnesses. The talk includes a demo of Omnigent’s workflow, including @opentelemetry traces in tools like @MLflow.
🗓️ Wed, Sept 23 | 6:00–9:30 PM GMT+2
📍 La Fondation, Paris
🎟️ Register:
#Paris# #Omnigent# #OpenSource#
Show more
From our recent Omnigent & Multi-Agent Coding Meetup in NYC, @dennylee (@databricks) gives a primer on why a meta-harness matters.
The talk covers:
🔹 Why coding agents and harnesses do not interoperate
🔹 How a meta-harness sits above Claude, Codex, Cursor, and similar tools
🔹 Multi-agent debates, where agents critique and improve each other’s code
🔹 Sharing a session so a teammate can view, comment, and run it if you grant them rights
🔹 Policies that require approval for file and shell operations
📽️ Watch now:
#Omnigent# #AIAgents# #NYC#
Show more
Agents that need live web data can now add nimble_research and nimble_extract to an agent spec by name, instead of wiring up your own scraping and search code. 👇
nimble_research hands a task to a @nimble_search Web Search Agent and returns per-claim citations with a confidence signal. It needs pip install 'omnigent[nimble]'. nimble_extract runs one of your Nimble extract templates against the live web and returns structured JSON. Both resolve inside the Omnigent runner.
For a quick lookup, set search_provider: nimble on web_search. That path needs no extra.
🔗 Read the full post:
#Omnigent# #AIAgents#
Show more
Jules Damji (@databricks) walks through what breaks when you switch coding harnesses: sharing context, carrying policies, and seeing whether the agents did the right thing. @omnigent_ai sits on top as a meta-harness; session-scoped traces go to MLflow.
📽️ Watch the tutorial:
#Omnigent# #MLflow# #OpenSource# @2twitme
Show more
Packed house last night for our Omnigent & Multi-Agent Coding Meetup at the @databricks NYC office! 🗽
Highlights from the night:
• Omnigent Overview
• Training Custom Agents for Enterprise Tasks
• Panel Q&A with @SpaceXAI, @Modal, and @Databricks
A big thank you to our speakers and everyone who came out! 👏
🔗 Stay in the loop on future events:
#Omnigent# #OpenSource# #NYC# #AI# #MultiAgent#
Show more
