Inspect the sources.

A Claude-centric coding agent with interactive and non-interactive workflows, explicit permissions, native sandboxing, MCP, skills, hooks, plugins, delegated agents, background sessions, and subscription or API authentication.

65 first-party sources are indexed on the canonical product profile.

OpenAI's coding agent across desktop, terminal, IDE, cloud, SDK, and CI, with default local sandboxing, managed permission policy, MCP, hooks, subagents, persistent memories, worktrees, browser tools, and optional local or custom model providers.

49 first-party sources are indexed on the canonical product profile.

An open-source, client-server coding agent across terminal, desktop, IDE, local web, SDK, and headless modes, with broad provider and subscription support, local models, granular permissions, MCP, parallel subagents, Git-backed undo and redo, and GitHub automation.

28 first-party sources and 1 discovery records are indexed on the canonical product profile.

An MIT-licensed terminal coding agent with a small core, broad provider and local-model support, JSON and RPC modes, and a TypeScript extension system for users who prefer to assemble their own workflow.

20 first-party sources are indexed on the canonical product profile.

An MIT-licensed terminal agent, invoked as `omp`, that layers LSP and debugger tooling, browser control, first-class subagents, MCP, ACP, RPC, and a large provider catalog onto Pi's extensible base.

24 first-party sources are indexed on the canonical product profile.

SpaceXAI's open-source terminal coding agent with TUI, headless and ACP surfaces, custom models, MCP, plugins, default-on subagents, plan review, conversation rewind, permissions, and optional OS-level sandbox profiles.

26 first-party sources are indexed on the canonical product profile.

Meta's terminal and CI coding agent with repository tools, default-on approvals and OS sandboxing, persistent memory, compaction, resumable sessions, goals, subagents, skills, hooks, and MCP.

17 first-party sources are indexed on the canonical product profile.

A mature terminal pair-programming tool with broad model support, local endpoints, Git-backed undo, a repository map, scripting, and automatic lint, test, and commit workflows.

18 first-party sources are indexed on the canonical product profile.

An open agent platform and developer control center with CLI, web, SDK, and automation surfaces; provider and local-model flexibility; MCP and browser tools; and local, Docker, or remote execution environments.

23 first-party sources are indexed on the canonical product profile.

An open-source general agent with desktop, CLI, and headless use, broad provider, subscription, and local-model access, plus built-in skills, MCP extensions, recipes, subagents, browser control, configurable approvals, and platform-specific isolation.

21 first-party sources are indexed on the canonical product profile.

An open-source agent for IDEs and the CLI with broad provider and local-model support, MCP, browser use, checkpoints, read-only research subagents, persistent agent teams, lifecycle plugins, and configurable approval workflows.

28 first-party sources are indexed on the canonical product profile.

An Apache-2.0 terminal agent for Gemini with interactive and non-interactive modes, MCP, Agent Skills, policy controls, optional OS or container sandboxing, specialized subagents, worktrees, and file-aware rewind and restore.

20 first-party sources are indexed on the canonical product profile.

A proprietary terminal interface to Google's shared Antigravity agent harness, with a managed multi-provider model catalog, asynchronous subagents, structured headless output, SSH use, browser actions, MCP, plugins, skills, hooks, granular permissions, and optional native OS sandboxing.

23 first-party sources are indexed on the canonical product profile.

GitHub's terminal coding agent supports interactive and programmatic execution, granular permissions, local and cloud sandboxes, MCP, custom agents, parallel subagents, file rollback, and GitHub-hosted or custom local models.

19 first-party sources are indexed on the canonical product profile.

A proprietary terminal surface for Cursor Agent with interactive and print modes, subscription model selection, MCP, Agent Skills, project rules, structured output, and allow or deny policies for shell commands and file access.

16 first-party sources are indexed on the canonical product profile.

JetBrains' coding agent runs in the terminal, CI, JetBrains IDEs, and a tethered remote web UI with subscriptions, BYOK and local models, MCP, approval controls, Agent Skills, parallel sessions, Git worktrees, and specialized subagents.

18 first-party sources are indexed on the canonical product profile.

Factory's proprietary agent combines an interactive CLI, structured headless execution, IDE integrations, many hosted or local models, MCP, custom subagents, worktrees, and tiered permission levels from read-only analysis to deployment workflows.

17 first-party sources are indexed on the canonical product profile.

ForgeCode is an open terminal coding harness that works interactively or as a one-shot command. The audited source defines 47 provider entries spanning hosted APIs, subscription access, local endpoints, and a context engine, plus MCP, skills and delegated agents. It runs on your machine by default; its `--sandbox` option separates Git work but does not contain commands.

24 first-party sources are indexed on the canonical product profile.

An Apache-2.0 terminal coding agent with persistent auto-memory, headless execution, hosted and local providers, MCP, specialized subagents, built-in desktop Computer Use, IDE integrations, checkpoints, and opt-in macOS or container isolation.

25 first-party sources are indexed on the canonical product profile.

Continue's Apache-2.0 agent runs in the terminal, VS Code, and JetBrains with interactive or headless execution, reusable model and MCP configuration, and allow, ask, or exclude policies for every tool.

4 first-party sources are indexed on the canonical product profile.

Mistral's Apache-2.0 coding harness combines an interactive CLI and ACP editor integration with local or hosted models, delegated subagents, MCP, skills, policy hooks, structured automation, durable sessions, and message-level file rewind.

31 first-party sources and 1 discovery records are indexed on the canonical product profile.

Moonshot AI's MIT-licensed coding harness provides a terminal UI, structured print mode, multi-provider routing, MCP, skills, plugins, hooks, ACP editor integration, a local web service, installable Computer Use and WebBridge tooling, trace inspection, and parallel foreground or background subagents.

18 first-party sources are indexed on the canonical product profile.

A multi-provider terminal coding harness with repository tools, persistent project memory, automatic context compaction, primary and delegated agents, bounded workflow orchestration, headless and local web surfaces, MCP, skills, and Git-backed undo. It runs tools on the host: its permission policy and workflow runtime are controls, not an operating-system sandbox.

16 first-party sources and 1 discovery records are indexed on the canonical product profile.

The stateful open-source harness formerly called Letta Code, with git-backed self-editing memory, skills, MCP connectivity, trusted runtime mods, foreground or background subagents, headless execution, schedules, multi-provider access, and selectable local, remote, or managed cloud environments.

29 first-party sources are indexed on the canonical product profile.

An MIT-licensed, multi-provider coding agent for VS Code, JetBrains, terminal, browser-hosted cloud, and CI, with delegated subagents, MCP, browser automation, Git snapshots, and an opt-in macOS or Linux sandbox.

28 first-party sources and 1 discovery records are indexed on the canonical product profile.

A multi-model terminal harness with interactive and headless modes, parallel subagents, MCP, policy-based permissions, worktrees, session checkpoints, hooks, skills, and IDE context integration.

20 first-party sources and 1 discovery records are indexed on the canonical product profile.

An open-source coding harness that coordinates specialized agents for finding files, editing, review, tests, research, and browser work. Use it interactively in the terminal or build deterministic agent workflows with its TypeScript SDK.

16 first-party sources and 1 discovery records are indexed on the canonical product profile.

A source-available terminal coding agent for interactive or scripted work, with multi-provider and local-model support, a Hyper subscription option, mid-session model switching, project sessions, LSP, MCP, skills, hooks, per-tool approvals, and parallel read-only research delegation.

20 first-party sources and 1 discovery records are indexed on the canonical product profile.

The open-source agent workspace formerly called Mux, for parallel coding tasks with custom agents, nested subagents, persistent scoped memory, compaction, MCP, local or container runtimes, policy files, editor integrations, and budgeted CLI goal runs.

27 first-party sources and 1 discovery records are indexed on the canonical product profile.

A beta, self-hosted coding agent for teams already using Coder. It works from a web chat or API, can create approved workspaces, delegate parallel subagents, and use the models and tools configured by an administrator.

20 first-party sources and 1 discovery records are indexed on the canonical product profile.

An Apache-licensed VS Code agent continuing the Roo Code lineage, with broad provider and subscription access, local models, custom modes, hierarchical subtasks, MCP, semantic indexing, worktree workflows, task history, and shadow-Git file checkpoints.

28 first-party sources and 1 discovery records are indexed on the canonical product profile.

A proprietary desktop agent environment with persistent goal state, independent completion checks, parallel and background subagents, scheduled tasks, scoped approvals, MCP, hooks, remote workspaces, and an integrated browser and review flow.

17 first-party sources and 1 discovery records are indexed on the canonical product profile.

An open-source Electron desktop IDE that combines a full Chromium browser, multi-provider and local models, managed project context, granular diff review, and user-orchestrated parallel agent sessions.

27 first-party sources and 1 discovery records are indexed on the canonical product profile.

An MIT-licensed general agent with terminal, desktop, web, API, and messaging surfaces; persistent memory and goals; coding and browser tools; nested parallel delegation; scheduled jobs; MCP; checkpoints; and local, container, SSH, or managed execution backends.

25 first-party sources and 1 discovery records are indexed on the canonical product profile.

An MIT-licensed general-purpose agent harness with an embedded model-and-tool loop, repository-capable file and shell tools, persistent memory and compaction, nested subagents, multi-agent routing, browser and MCP integrations, durable background automation, and optional container isolation.

31 first-party sources are indexed on the canonical product profile.

A deliberately small open-source software-engineering agent with one linear bash-only loop, confirm, yolo, and human control modes, versioned trajectories, local-model routing, optional isolated environments, and batch evaluation runners.

23 first-party sources are indexed on the canonical product profile.

A proprietary multi-model coding agent with terminal, editor, and web control, non-interactive and runner modes, durable cloud orbs, schedules, event-driven webhooks, live multiplayer threads, MCP, skills, plugins, and built-in or programmable subagents.

21 first-party sources are indexed on the canonical product profile.

A proprietary coding CLI with interactive and headless execution, custom and parallel agents, MCP, steering, hooks, resumable sessions, goal loops, and an optional classic checkpoint system; CLI 3.0 adds a separate early-access harness and policy format.

21 first-party sources are indexed on the canonical product profile.

Poolside's proprietary-distribution CLI combines interactive and JSONL automation modes, ACP client and server roles, OpenRouter and local OpenAI-compatible models, MCP, skills, worktrees, structured trajectories, and optional local container sandboxes.

15 first-party sources are indexed on the canonical product profile.

An MIT-licensed terminal coding agent whose last public release was July 2025. Its maintained-era design combined persistent plans, project maps, model-role packs, cumulative diff review, command debugging, and rewind; the hosted cloud later wound down, so the remaining path is a dormant self-hosted codebase.

25 first-party sources are indexed on the canonical product profile.

An early-stage, model-agnostic terminal coding agent that defaults to a hardened Docker container, supports direct host execution, coordinates bounded subagents, offers configurable multi-model counsel and two-round debate panels, connects MCP and optional browser tools, and separates session state from a provenance-aware durable memory store.

6 first-party sources and 1 discovery records are indexed on the canonical product profile.

LangChain's terminal coding product built on Deep Agents and LangGraph, with an interactive TUI, non-interactive pipeline runner, custom subagents, MCP, local session checkpoints, persistent memory, approval gates, and integrations for managed remote sandboxes.

9 first-party sources and 1 discovery records are indexed on the canonical product profile.

An Apache-licensed general agent platform that qualifies as a coding harness through its adaptive tool loop, repository and shell tools, managed session context, and runtime permission modes. It adds delegated sessions, MCP bridging, one-shot CLI runs, replay diagnostics, memory, web and desktop surfaces, and multiple messaging channels.

9 first-party sources and 1 discovery records are indexed on the canonical product profile.

A proprietary product with public versioned npm packages for its multi-turn agent loop, coding tool pack, persistent memory, headless runner, MCP client, browser automation, and lightweight terminal UI, plus an IDE-oriented product surface spanning multiple model providers.

8 first-party sources and 1 discovery records are indexed on the canonical product profile.

A young MIT-licensed personal agent that qualifies as a coding harness through its iterative tool loop, repository and shell mutation, persistent JSONL and vector recall, tool scopes, background runtime, MCP, local Ollama path, and parallel read-only subagents across terminal, web, desktop, and messaging clients.

13 first-party sources and 1 discovery records are indexed on the canonical product profile.

An MIT-licensed coding harness whose Go runtime implements an adaptive model-and-tool loop, repository and shell mutation, automatic context compaction, project memory, resumable JSONL sessions, provider switching, subagents, persistent teammates, independent worktree workers, policy modes, hooks, traces, checkpoints, MCP, and browser automation.

22 first-party sources and 1 discovery records are indexed on the canonical product profile.

An alpha terminal coding harness distributed as a self-contained binary, with repository and shell tools, explicit goal loops, automatic context compaction, persistent project memory, delegated subagents, local GGUF inference, MCP, skills, headless runs, and a structured server protocol. Local execution is host-first: permissions and tool filters govern calls but do not establish an operating-system sandbox.

17 first-party sources and 1 discovery records are indexed on the canonical product profile.

An MIT-licensed coding harness whose Rust runtime implements an adaptive model-and-tool loop, repository and shell mutation, automatic and transaction-safe context maintenance, durable project memory, delegated agents, MCP, skills, policy rules, OS shell sandboxing on supported platforms, persistent checkpoints, and structured headless execution. The same core is exposed through terminal, desktop, local web, editor, and automation surfaces.

28 first-party sources are indexed on the canonical product profile.

An MIT-licensed terminal coding harness with an adaptive tool loop, interactive and headless modes, persistent memory, branchable and resumable session trees, MCP and skills, local-model routes, optional OS or external sandboxes, and ledger-backed multi-worker fleets.

16 first-party sources are indexed on the canonical product profile.

An MIT-licensed Python harness that owns a streaming tool loop, repository tools, compaction and persistent memory, permissions and hooks, optional OS or Docker sandboxes, provider and subscription routing, headless output, and multi-agent coordination.

10 first-party sources are indexed on the canonical product profile.

A proprietary coding harness from Random Labs for repository-scale terminal work, with provider and model-slot selection, granular tool permissions, session steering and resume, parallel and background subagents, reusable skills, MCP, long-running shells, headless structured output, and an HTTP server mode. Execution is host-first: permissions govern tool calls but the reviewed documentation does not establish an operating-system sandbox.

8 first-party sources and 1 discovery records are indexed on the canonical product profile.

A local coding harness from Aexol that reads and writes repository files, runs shell and Git commands, iterates toward explicit goals, compacts and recalls session context, delegates work to isolated-context subagents, and connects either through a terminal UI or a browser relay. Execution is host-first: the reviewed documentation does not establish an operating-system sandbox or a general tool-permission policy.

7 first-party sources and 1 discovery records are indexed on the canonical product profile.

DeepSeek AI's MIT-licensed developer-preview harness combines a local Web UI, a headless CLI, a Python SDK, multi-provider routing, durable sessions and compaction, policy-controlled repository tools, OS file-effect sandboxing, skills, optional MCP, and parallel or continuable subagents.

15 first-party sources are indexed on the canonical product profile.

A local kanban control plane for parallel Claude Code, Codex, experimental Cursor Agent, and Gemini CLI tasks, isolated worktrees, structured approvals, and review.

6 source, preview, and code-audit records are indexed on the canonical GUI profile.

A cross-platform Cowork app for many named coding agents, parallel sessions, visual file changes, automation, and browser access.

6 source, preview, and code-audit records are indexed on the canonical GUI profile.

A browser-based, multiplayer workspace that runs agent CLIs on a team runner.

4 source, preview, and code-audit records are indexed on the canonical GUI profile.

A native Claude Code workspace with searchable local history, up to six live panels, worktree-aware grids, diffs, terminal, and preview.

4 source, preview, and code-audit records are indexed on the canonical GUI profile.

The Code tab in Claude Desktop, using the Claude Code engine with dedicated developer panes.

4 source, preview, and code-audit records are indexed on the canonical GUI profile.

A desktop, server, browser, and mobile workspace for many ACP coding agents, delegation, split views, worktrees, Git, and diffs.

5 source, preview, and code-audit records are indexed on the canonical GUI profile.

The dedicated Codex coding experience inside the ChatGPT desktop app.

4 source, preview, and code-audit records are indexed on the canonical GUI profile.

A Mac control plane for parallel coding agents in local worktrees or isolated cloud microVMs.

3 source, preview, and code-audit records are indexed on the canonical GUI profile.

A local-first desktop environment for parallel coding agents, review, and issue-to-agent workflows.

3 source, preview, and code-audit records are indexed on the canonical GUI profile.

A local-first web, PWA, and Telegram control surface for handing off five coding-agent CLIs between terminal and remote devices.

4 source, preview, and code-audit records are indexed on the canonical GUI profile.

An open-source desktop workspace for running and coordinating multiple named coding agents across sessions and worktrees.

6 source, preview, and code-audit records are indexed on the canonical GUI profile.

A visual editor and session manager for agent work across documents, mockups, code, tasks, Git, and shared team artifacts.

9 source, preview, and code-audit records are indexed on the canonical GUI profile.

An OpenCode-native workspace across desktop, web, editor, and mobile with multi-run worktrees, diff review, previews, GitHub flows, and remote access.

4 source, preview, and code-audit records are indexed on the canonical GUI profile.

A visual OpenHands workspace for parallel agents, per-conversation worktrees, diffs, local or remote backends, automations, and ACP harnesses.

6 source, preview, and code-audit records are indexed on the canonical GUI profile.

A self-hosted web and Slack control plane for scoped, durable agent work across four named harnesses.

5 source, preview, and code-audit records are indexed on the canonical GUI profile.

The first-party Qwen Code desktop shell with multi-session and split views, optional worktrees, visual Git diffs, and a bundled local runtime.

7 source, preview, and code-audit records are indexed on the canonical GUI profile.

A local desktop code editor for many CLI agents running in isolated Git worktrees.

7 source, preview, and code-audit records are indexed on the canonical GUI profile.

A minimal web and desktop GUI that presents five coding harnesses through one session model.

4 source, preview, and code-audit records are indexed on the canonical GUI profile.

An open-source desktop control plane for multi-provider agent tasks with shared context, worktrees, diffs, remote hosts, and team access.

8 source, preview, and code-audit records are indexed on the canonical GUI profile.

A self-hosted browser dashboard that owns worktrees, tmux layouts, agent events, services, and optional containers.

6 source, preview, and code-audit records are indexed on the canonical GUI profile.