Ovren

omnirush.ai is a desktop coding agent for macOS and Linux that works on local projects. It lets users select models and effort levels, add provider keys, and configure skills and MCP servers. Its Git workflow can clone repositories, create branches and worktrees, make commits, push changes, and open or review pull requests through gh, with approval prompts for tool calls and write commands. The app is distributed through platform-specific installers and releases under the repository's MIT terms, while code in the ee/ directory has a separate license.

OpenWorker is an open-source desktop AI coworker that produces finished deliverables from everyday tasks, including code-security reviews with proposed fixes, cloud-configuration audits, incident reports, documents, spreadsheets, drafted messages, and scheduled briefs. It runs on the user's machine through a native desktop app and a local Python agent server built on aisuite, working across local files, the terminal, connected applications, and more than 25 connectors. Specialist coworkers cover security review, cloud posture, incident triage, everyday work, and recurring automations; security review combines deterministic scanners such as Semgrep with model reasoning, then re-scans and diff-reviews proposed fixes before approval. The agent breaks requested outcomes into steps and uses models from providers such as OpenAI, Anthropic, and Google, open-weight providers, or a local Ollama deployment, with the user supplying model access. Consequential actions—including sending messages, changing calendars, and running commands—are approval-gated. Its governance design includes human-only floors for dangerous or irreversible operations, explicitly granted and revocable autonomy rules, circuit-breaker escalation for uncertain or repeatedly denied actions, and an audit trail recording tool calls, approval provenance, and reviewer reasoning; unattended runs cannot self-approve. The project is in open beta and provides downloads for macOS on Apple Silicon and Windows on x64.

Open Code Review is an open-source, AI-powered command-line code-review tool developed from Alibaba Group’s internal review assistant. It reads Git diffs and sends changed files to a configurable LLM through an agent with tool-use capabilities; the agent can read complete files, search the repository, and inspect other changed files for context before producing structured comments tied to source lines. Its hybrid architecture combines deterministic engineering with dynamic agent decisions: deterministic stages select and bundle files, match rules to file characteristics, and apply independent comment-positioning and reflection modules, while scenario-specific prompts and tools guide context retrieval and review. The `ocr scan` command audits complete files or directories without requiring a meaningful diff, and the project provides multilingual rules for issues including null-pointer exceptions, thread safety, cross-site scripting, and SQL injection. It supports configurable model endpoints, including OpenAI- and Anthropic-compatible endpoints, and requires Git 2.41 or newer.

Omnara is an open-source managed agent platform for running AI agents as a service on any compatible model and machine. It provides a REST API, TypeScript SDK, CLI, dashboard, and MCP server for launching agents, sending messages, streaming events, and handling approvals. The platform runs agent workers that build model context, call models, and execute tools, while PostgreSQL stores each agent's event log and durable state so workers can resume agents after crashes, restarts, or machine disconnections. Agents can use built-in tools, skills, MCP servers, custom tools, persistent memory, subagents, permissions, schedules, webhooks, and integrations with Slack, Discord, and GitHub. Machines connect through the Omnara daemon and may be local laptops, virtual machines, containers, or managed sandboxes; agents can run across multiple machines without inbound ports. Omnara Cloud is available at app.omnara.com, and the platform can be self-hosted with Docker Compose under the Apache License 2.0. Self-hosted deployments keep agent history in the operator's PostgreSQL database and can use any supported model provider or compatible self-hosted endpoint.

OpenHands is an open-source AI coding-agent platform for building and running software-development agents locally, in cloud sandboxes, or in controlled enterprise environments, using closed or open-weight models and supporting parallel execution. Its Agent Canvas connects to local, remote, or cloud agent backends, including Docker containers, virtual machines, OpenHands Cloud or Enterprise infrastructure, and ACP-compatible agents such as Claude Code, Codex, Gemini CLI, Pi, and OpenCode. Automation workflows run on schedules or webhook events and integrate with services including GitHub, Slack, Jira, Linear, Notion, and Datadog for tasks such as pull-request review, CI-failure remediation, issue triage, QA checks, incident investigation, documentation updates, and recurring engineering work. OpenHands supports MCP connections to internal tools, APIs, and data sources, along with enterprise controls for execution isolation, access permissions, auditing, usage, budgets, and organizational policies. The repository includes the Agent Canvas frontend, backend selection, local-stack orchestration, and an Agent Server REST API for running multiple agents on a host; related repositories provide the SDK, TypeScript client, and automation services.