Agents

Open-source, local-first workspace where humans and AI coding agents coordinate through channels, tasks and persistent memory.

AI agent workspace for developers that runs parallel coding sessions with approval prompts, Git context and subagents.

Python port of the opencode coding agent with a CLI, a FastAPI server and MCP client support.

Local desktop and web workbench that reviews a repo's pull requests with Claude or Codex in isolated worktrees and posts only approved comments.

Go reimplementation of the pi coding agent with headless and REPL modes, skills, plugins and multi-provider support.

Local-first AI coding terminal that grounds model output in real files, tools, permission checks and verification steps.

Desktop AI agent that runs on your machine, edits project files and runs commands, and produces Word, Excel, PowerPoint and PDF files.

Local-first AI desktop assistant that reads and writes files, runs commands and builds reports on your machine, with skills and IM bots.

Single-binary, DeepSeek-native terminal coding agent with a code graph, local OCR, model routing and an OS sandbox.

Local-first open-source desktop coding agent that uses your own LLM key and can index repos with an optional context engine

Voice-activated LLM agent for Raspberry Pi that runs Ollama models fully on the device and can run custom tools.

Terminal coding agent with per-request model routing across six cost tiers, a code graph and spend monitoring, served by a hosted router.

Terminal coding assistant from iFlow that is scheduled to shut down on April 17, 2026.

Terminal AI coding agent that plans and applies changes across large projects, with a diff review sandbox.

LLM agent workflow that assists a human researcher through literature review, experiments and report writing.

Coding agent with a CLI and VS Code extension that reads whole projects, runs file and shell tools, and supports MCP and Hooks.

Local-first desktop orchestrator that runs specialist coding agents such as Claude Code, Codex and Gemini in one shared workspace.

Sales platform with AI agents, B2B contact data, multichannel sequences and parallel dialing for sales teams.

ASAPP CXP platform whose GenerativeAgent resolves customer issues, with human-in-the-loop controls and observability.

Augment's Cosmos platform runs agent loops for code review, ticket-to-PR, vulnerability fixes and incident response, with a CLI and IDE plugins

CrowdStrike's agentic AI for security operations that coordinates agents to triage detections, investigate and run governed responses.

Anthropic's browser extension that reads the pages you are signed in to and clicks, types and fills forms for you

DevOps agent that checks production after each change, flags regressions and handles alerts, opening fix PRs for review.

Mac app that runs parallel Claude Code, Codex and Cursor agents in isolated workspaces and lets you review and merge their changes.