Projects sharing features with OpenBot

OpenDots is a platform for hosting long-lived AI agents, called dots, that keep running over time instead of living inside a single short chat. Each agent gets its own sandboxed computer with a browser, files, and a terminal that persist across restarts, with permission checks, an action record, and the option for a human to take over. The same AI coworker carries one conversation across written chat, real-time voice calls, and Slack, and a workspace of shared spaces and nested pages sits alongside it. People stay in control of what agents do. The chat interface streams agent activity live, w

Omnigent is a policy-governed orchestrator for coding agents. It runs several agent harnesses, such as Claude Code and Codex, together in one session, and a single harness identifier decides which agent handles a session, so teams can swap agents without rewriting their definitions. Sub-agents can each use their own harness, model, prompt, and sandbox inheritance, which lets one agent review another's work or split a task with it. Every agent action passes through layered policies set at the server, agent, and session levels. Each policy function allows, denies, or abstains, and a denial stop

Mission Control is a self-hosted web dashboard that acts as a control plane for autonomous AI coding agents. It lets operators register and monitor a fleet of agents across runtimes, dispatch tasks to them, review their runs, and track token spend, all from one interface backed by role-based access and an audit log. Work reaches agents through priority queues, direct assignment, cron-driven recurring templates, and multi-step pipelines that chain one agent's output into the next. Agents claim the highest-priority task atomically, and completed work can be routed through a quality-review gate

Cascadeflow is a runtime for AI agents that cuts language model spend by trying an inexpensive drafter model first, validating the answer, and escalating to a stronger verifier only when quality falls short. It also works as a budget and policy enforcement layer inside the agent loop, applying spending caps, compliance rules, and allow, switch-model, deny-tool, or stop actions at each step, with an audit trail of the decisions taken. Each call reports the model used, its cost, and the savings. What sets it apart is how it plugs into existing code. It can run as a local gateway that speaks the

This is an open-source, self-hosted customer relationship manager built around autonomous AI agents. A durable background agent with its own work queue researches contacts, companies and deals, decides what to examine next, schedules follow-up rechecks with a stated reason shown to the sales rep, and stays within a research budget while no one is present. Each contact, company and deal also has a chat tab where you can talk to the agent, see its steps, discarded leads and questions, and keep the conversation across page reloads. What sets it apart is how it treats what the agent finds. Facts

Open Connector is a self-hosted gateway that lets AI agents and applications run actions on connected SaaS accounts without ever handling the underlying credentials. It keeps API keys, OAuth clients and custom credentials encrypted inside the gateway, applies them only when an action executes, and ships with a searchable catalog of ready-made connectors for products such as GitHub, Gmail, Notion, Slack and BigQuery. Each catalog entry includes reviewable request and response schemas and required scopes. The same action model can be reached through a TypeScript client, a command-line relay, a

Atmosphere is a Java-based framework for building and coordinating AI agents. It provides a real-time transport layer for streaming data via WebSockets, SSE, gRPC, and WebTransport, alongside a multi-agent orchestration framework for managing agent fleets through sequential, parallel, and graph-based execution workflows. The project features a durable workflow engine that persists agent state as snapshots, allowing long-running tasks to survive system restarts and incorporate human-in-the-loop approvals. It also implements Model Context Protocol servers to expose tools, resources, and prompt

Ekko Studio is a self-hosted AI agent workspace that runs several agents together in shared chats and keeps sessions and data on the user's own machine. It streams replies, tool traces, and generated-file previews across persistent sessions, and it hosts group rooms where multiple agents answer when mentioned. It also detects, installs, configures, and launches third-party command-line coding agents from one interface, with built-in terminals, session history, a workspace picker, and file diffs. Beyond chat, the workspace includes a visual canvas for building runnable agent workflows with con

This is a Python SDK for building asynchronous AI agents. A single async session connects to an agent backend, sends prompts (text or multimodal content such as images and documents), and streams results back as steps, text tokens, model thoughts, and tool calls. The session handles backend startup, authentication, tool wiring, hook registration, and cleanup, so developers don't write the agentic loop by hand. Agents run through a locally running harness on the developer's own machine, and the package ships with a pre-compiled platform-specific binary. What sets it apart is how much of the ag

PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo

Claudecodeui is an open-source web interface that orchestrates multiple AI coding agents from different providers—including Claude Code, Cursor CLI, Codex, and Gemini CLI—side by side in isolated cloud environments. It functions as a multi-provider orchestration platform, allowing users to run agents from different tools within the same workspace without being locked into a single vendor. The platform runs each agent session inside a hypervisor-level Docker sandbox that isolates filesystem, network, and process access, with sessions persisting in the cloud to survive network disconnection or

This is an open-source Python SDK for building and orchestrating production-grade AI agents. It provides a unified framework for creating conversational agents that can use tools, maintain state, and coordinate across multiple language model providers including OpenAI, Anthropic, Google, Amazon Bedrock, and locally-hosted models. The SDK supports multi-agent orchestration through graphs, teams, and swarms, allowing several specialized agents to collaborate on complex tasks. Agents can be composed as callable tools that other agents invoke, and the framework includes policy handlers that inspe

Paperclip is an LLM agent orchestration platform and governance suite designed to coordinate teams of autonomous AI agents. It provides a management plane for defining organizational hierarchies, assigning roles, and aligning individual agent tasks with a structured mission tree to ensure work maps to business objectives. The project distinguishes itself through a specialized agent skill registry and workspace manager. It allows for the discovery and injection of reusable workflows into agent runtimes without retraining and provides isolated, sandboxed execution environments with persistent s

Ragent is a Java application for building agentic retrieval-augmented generation systems, aimed at question answering over managed enterprise knowledge bases. A reasoning agent works in a reason-and-act loop. It decides when to search knowledge, call tools, or use skills before it answers. Answers stream to the client as separate events for thinking, answer text, cited sources, and suggested follow-up questions, and running work is cancelled if the client disconnects. Retrieval runs vector, keyword, knowledge-graph, and web searches in parallel. It then deduplicates the results, merges them w

Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech systems. It utilizes a frame-based data pipeline to route audio, video, and text through a modular sequence of processors, enabling the orchestration of low-latency conversational AI. The project is distinguished by its ability to coordinate complex multimodal services, including speech-to-text, language models, and text-to-speech, within a single pipeline. It features semantic voice activity detection for natural turn-taking, state-machine conversation flows for dialogue manag

Cumora is a cross-platform team chat where AI agents join humans as teammates in shared rooms, direct messages, and group conversations. Agents sit in the same roster as people, show availability states such as working, thinking, or resting, and coordinate with humans through a shared Kanban board, calendar, collaborative documents, and email. The same web codebase ships as a browser app, an Electron desktop app, and Capacitor-wrapped iOS and Android apps. Agents can be hosted in two ways. A self-hosted server stack runs each cloud agent in its own isolated Kubernetes pod with shell, file, br

Ory Keto is an open-source authorization server that implements Google Zanzibar’s relationship-based access control model. It stores every access relationship as a tuple in a SQL database and exposes a declarative TypeScript-like namespace language for defining object types, relations, and permissions. The service provides bidirectional permission resolution, configurable consistency levels for checks, and dual gRPC and REST APIs for broad integration. Keto extends the Zanzibar model with edge enforcement of access policies, structured compliance auditing of permission decisions, and infrastr

This repository is a collection of example projects and guides for building with Cursor's coding agents. The samples cover running agents from TypeScript code against local workspaces or cloud runtimes, streaming their output live, and launching them from a terminal. Other examples include a cloud agent kanban dashboard, a task graph orchestrator, an app-prototyping chat, and a realtime voice intake demo. Several samples go beyond a basic quickstart. The kanban dashboard lists cloud agents as cards grouped by status, repository, or branch, previews their artifacts, and launches new agents fro

Honcho is an agent memory platform: a server and set of SDKs that store conversation history as messages and reason over it in the background to build persistent, evolving context about users and agents. It models humans, agents, groups, and projects as equal peers who join shared sessions inside isolated workspaces, and it derives conclusions about each participant so applications can adapt their responses to the person they are talking to. What sets it apart is the reasoning layer. Queued messages are processed in order per session, and scheduled consolidation passes draw deductive and indu

GenOffice is an open-source desktop office suite with editors for Word, Excel and PowerPoint style files, plus PDF, Markdown and HTML, and a built-in AI agent that drafts and revises documents. Files are opened, edited, converted and searched on the user's own machine, and a network connection is needed only for the AI features, which run on the user's own model keys. Several things set it apart. Edits are applied as narrow patches that leave every untouched part of the original file byte-for-byte intact, so documents stay compatible with Microsoft Office. In Word files, AI rewrites appear as

Claurst is a terminal-based AI coding agent written in Rust. It runs an interactive text interface where the agent reads, edits and ships code alongside the developer, and it is built without telemetry or tracking. The same program can also run headlessly in scripts and automated pipelines. A single interface sits in front of multiple AI model providers, applying one shared retry policy and context compaction so the same workflow works with whichever provider is chosen. Shell commands run in an isolated sandbox that limits writes to the workspace and blocks network access by default, with app

Monocode is a native desktop application, written in Rust, that runs several installed AI coding agent command-line tools from one interface. It reuses each tool's existing sign-in and the user's own subscriptions rather than selling tokens. Sessions live in tabs and split panes grouped by project, and each parallel task can run in its own Git worktree, so several agents can work on the same project without overwriting each other's files. Beyond running a single agent, it supports splitting work across up to four worker agents, handing a session to another model with a recap, and continuing p

Zeroclaw is a modular framework for building and deploying autonomous agents that integrate AI models, messaging platforms, and hardware interfaces. It functions as a multi-agent orchestrator and embedded systems controller, providing a unified runtime for managing agent lifecycles, memory, and security policies across diverse environments. The system distinguishes itself through its focus on secure, verifiable hardware and software orchestration. It enforces strict security boundaries, including command allowlisting, resource throttling, and interactive human-in-the-loop approval for sensiti

Awesome Copilot is a comprehensive framework for autonomous software development, providing the infrastructure to orchestrate multi-agent teams and automate complex coding workflows. It functions as a centralized platform for managing AI-driven development, enabling developers to deploy specialized agents that interact with local files, terminal commands, and external APIs to execute end-to-end software delivery tasks. The project distinguishes itself through its focus on governance and extensibility, offering a suite of security controls, policy-based execution guardrails, and audit trails t

Briefer is an interactive data notebook platform and business intelligence dashboard tool used for collaborative data analysis and reporting. It provides a containerized environment for building reports that combine SQL, Python, and Markdown with native visualizations. The platform features an integrated code assistant that uses large language models to generate SQL and Python snippets from natural language prompts. It is designed as a Kubernetes data application, deploying via Helm charts to manage isolated compute environments and ensure separate resources per page through pod-based isolati

mcp-context-forge is a Model Context Protocol federation gateway that unifies diverse AI tool servers and APIs into a single consistent interface for discovery and execution. It acts as a centralized proxy that aggregates multiple servers and APIs, allowing AI agents to access and invoke a unified set of tools, prompts, and resources. The project distinguishes itself through a multi-protocol translation bridge that converts communication between standard I/O, SSE, gRPC, and REST to enable interoperability between disparate tool servers. It includes a comprehensive LLM evaluation framework for

Ironclaw is an LLM orchestration framework and AI agent gateway designed to connect large language models with external tools, messaging interfaces, and persistent memory systems. It functions as a communication layer that routes interactions between users and AI models via HTTP webhooks and various messaging channels. The system focuses on secure tool execution through a WebAssembly sandbox and isolated containers, which allows the framework to run untrusted code and dynamically generate new tools from natural language descriptions. Security middleware provides prompt injection defense and s