CodeHerder vs the agent-orchestration field
See CodeHerder next to 14 other agent tools, cell by cell. Each cell shows what the vendor publishes, and each page names its sources and dates.
- 14
- Tools compared, tier by tier
- 20
- Capabilities scored in the matrix
Current as of 2 November 2026.
Three shapes of tool
People call many products "AI coding agents". They come in three shapes. Know the shape before you compare feature lists.
- The assistant. It lives in one person's editor or terminal. You steer it turn by turn. It suits one developer who wants help while they work.
- The single cloud agent. You give it one task and it works alone in the vendor's cloud. The vendor owns and bills the machines. It suits one well-defined task that you can hand off in full.
- The herd. Many agents work on many tasks at the same time, on machines you already own. A control plane assigns the work and enforces the rules. It suits a team that needs visible, accountable AI work at scale.
CodeHerder is the third shape. The table below compares it with other tools that build toward the same shape. It also lists a few single-agent products that buyers often put on the same shortlist.
20 capabilities, 15 platforms
Every cell traces to a source dated below. Read this before the table:
- ✅ published + sourced
- the vendor's own site/docs/announcement states this, with a source cited on the competitor's own page below.
- ⚠️ partial/qualified
- published, but narrower, differently-scoped, or hedged relative to CodeHerder's own version of the capability; see the footnote where one exists.
- "not published"
- no public evidence was found. This is not proof the vendor is missing the feature — it may exist and simply not be marketed. Never read a "not published" cell as a competitive claim of absence.
- unverified
- some signal exists (a transcript mention, a third-party comparison) but no primary source was located this pass.
"Not published" means no public evidence was found, not that the feature doesn't exist. A vendor may build and simply not market something. Treat every "not published" cell as absence of evidence, never as evidence of absence.
Verified as of 2026-11-02.
| Capability | CodeHerder | Orchestratia | Gas City/Gasworks | Warp Oz | Coder Agents | GitHub Agent HQ | Stoneforge | Factory | Devin | Codex app + Symphony | Claude Code Agent Teams | Augment Intent | OpenHands | Verdent | Cursor |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Concurrent agents | Published | Published | Published | Published | Published | Published | Published | Published | Published | Published | Published | Published | Published | Published | Published |
| Multi-vendor harnesses | Published | Published | Published | Published | Published | Published | Published | Not published (as of 2026-11-02) [1] | Not published (as of 2026-11-02) [1] | Partial [2] | Not published (as of 2026-11-02) [1] | Published | Published | Unverified | Not published (as of 2026-11-02) [1] |
| Customer-owned machines | Published | Published | Published | Published | Published | Partial [3] | Published | Published | Not published (as of 2026-11-02) | Partial [4] | Partial [4] | Partial [4] | Published | Unverified | Partial (self-hosted workers) |
| Multi-machine routing | Published | Published | Partial [5] | Published | Published | Partial [3] | Not published (as of 2026-11-02) | Published | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Published | Not published (as of 2026-11-02) | Partial (worker pools) |
| Automatic work assignment | Published | Published | Published | Published | Partial [6] | Partial [6] | Published | Published | Published | Published | Published | Published | Unverified | Published | Not published (as of 2026-11-02) |
| Capability-based routing | Published | Published | Partial (configurable) | Unverified | Unverified | Partial | Not published (as of 2026-11-02) | Published | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Partial (human-picked tier) | Partial | Not published (as of 2026-11-02) | Partial | Not published (as of 2026-11-02) |
| Atomic claiming | Published | Unverified | Partial (work queue) | Unverified | Unverified | Not published (as of 2026-11-02) | Published | Unverified | Unverified | Partial | Partial | Unverified | Unverified | Unverified | Not published (as of 2026-11-02) |
| Dependencies | Published | Published | Published | Partial | Not published (as of 2026-11-02) | Partial (issue-based) | Published | Partial | Partial | Not published (as of 2026-11-02) | Published | Partial | Not published (as of 2026-11-02) | Partial | Not published (as of 2026-11-02) |
| Custom workflows | Published | Partial (approval rules, not a stage schema) | Published (fully programmable) | Published | Partial (governance, not authoring) | Partial (Actions integration) | Partial (one fixed pipeline) | Partial | Not published (as of 2026-11-02) | Published (spec) | Not published (as of 2026-11-02) | Partial | Unverified | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) |
| Server-enforced gates | Published | Published | Published | Partial | Partial | Partial | Published | Unverified | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Partial (local hooks) | Published | Not published (as of 2026-11-02) | Partial | Not published (as of 2026-11-02) |
| Agent handoffs | Published | Published (contracts) | Published | Partial (context) | Not published (as of 2026-11-02) | Partial (PR/context) | Published | Partial | Published (coordinator) | Partial | Published (mailbox) | Published (spec-based) | Not published (as of 2026-11-02) | Unverified | Not published (as of 2026-11-02) |
| Persistent shared memory | Published | Not published (as of 2026-11-02) | Published (packs/state) | Published | Unverified | Partial (repo/AGENTS.md) | Partial (JSONL state) | Unverified | Partial (trajectory learning) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Partial (context engine) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) |
| Live terminal / view | Published | Published | Published | Partial (logs) | Partial | Partial (session logs) | Published | Unverified | Published (session link) | Partial (diff thread) | Partial (optional tmux) | Published | Unverified | Unverified | Unverified |
| Human takeover / steer | Published | Published | Published | Published | Unverified | Published | Partial | Unverified | Published | Partial | Published | Published | Unverified | Unverified | Unverified |
| Cost per task | Published (not Cursor sessions) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Partial (credits) | Unverified | Partial (metrics dashboard) | Not published (as of 2026-11-02) | Unverified | Published (ACU) | Not published (as of 2026-11-02) | Partial (token usage) | Partial (credit pool) | Unverified | Unverified | Unverified |
| Cost per stage/model | Published | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) |
| Hard $ cap | Published (checked periodically) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Partial (monitor, pause, stop) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Partial (spend limits) |
| Schedules | Published | Unverified | Published | Published | Not published (as of 2026-11-02) | Published (Actions) | Not published (as of 2026-11-02) | Published | Published | Published (Automations) | Not published (as of 2026-11-02) | Unverified | Published | Unverified | Unverified |
| Webhooks / API / CLI | Published | Published | Published | Published | Published | Published | Published | Published | Published | Published | Partial (CLI only) | Unverified | Published | Unverified | Published |
| Self-host full platform | Published (Enterprise) | Partial (Enterprise/custom) | Published (OSS) | Published (Enterprise) | Published | Not published (as of 2026-11-02) | Published (OSS) | Partial (Droid Computers only) | Not published (as of 2026-11-02) | Partial (spec only, not the app) | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) | Published | Not published (as of 2026-11-02) | Not published (as of 2026-11-02) |
- Factory (Droids), Devin, and Claude Code Agent Teams are each vertically integrated — the product's whole thesis is a single vendor's own agent(s), so "multi-vendor harness support" isn't just unpublished, it's outside the product's own stated shape. Still written as "not published" rather than a claim of proven absence, per this tree's own rule.
- The Codex *app* is Codex-only; the Symphony *spec* is model-agnostic by design and has community forks substituting Claude Code, but its reference implementation and default is Codex.
- GitHub Agent HQ orchestrates across github.com, VS Code, mobile, and CLI — powerful distribution, but not a "register the customer's own server" model the way Orchestratia's SSH-tunnel daemon or Factory's Droid Computers are.
- Codex app, Claude Code Agent Teams, and Augment Intent each run locally on the operator's own single machine (a real customer-owned-compute story for that one machine) but do not publish a *fleet* model spanning multiple customer-owned machines the way CodeHerder, Orchestratia, Gas City, Warp Oz, Coder Agents, Stoneforge, and Factory do.
- Gas City is self-hostable and OSS, which implies multi-machine capability, but no source found describes an explicit cross-machine routing mechanism the way Orchestratia's multi-server dashboard or Warp Oz's fleet model do.
- Coder Agents and GitHub Agent HQ both provision/trigger work from many entry points (chat, API, CI, Slack, Jira for Coder; assign-across-repos for GitHub) but the assignment step itself reads as more human-directed than an automatic router picking the agent.
Notice a cell that's out of date? Tell us and we'll fix it.
Already picked a tool and it shut down on you? /alternatives covers what carries over from Vibe Kanban, Terragon, and Crystal.
Read the full page for any of them
Each page names the pages we checked and dates what we verified. Comparing against hiring a person instead? Read freelancer or agents.
Direct shape match
Orchestratia
A dashboard that coordinates Claude Code, Gemini CLI, and Codex across servers you already run. It is in early access.
Gas City / Gasworks
Steve Yegge's programmable agent platform. A durable, Git-backed work tracker plus TOML formulas that become multi-stage agent workflows.
Warp Oz
Warp's cloud platform for coding agents. It runs many sandboxed agents in parallel and works with several harnesses.
Coder Agents
A self-hosted agent orchestrator from Coder. It works with many models and suits platform teams that need to govern models, prompts, and skills.
GitHub Agent HQ
GitHub's hub for agents from several vendors, built into the repository host that most teams already use.
Stoneforge
An open-source (Apache-2.0) agent orchestrator. A Director plans, Workers run in isolated worktrees, and Stewards test, merge, or send work back.
Factory
An agent platform for the whole software lifecycle, aimed at large companies. It includes Droid Computers: persistent machines you can register yourself.
Vertically integrated platform
Devin
Cognition's autonomous coding agent. It can now manage other Devins, each on its own VM.
OpenAI Codex app + Symphony
OpenAI's command center for Codex agents. Symphony is an open specification that turns an issue tracker into the control plane.
Claude Code Agent Teams
An experimental Anthropic feature. A Claude Code team lead starts teammates, each with its own context window. A shared task list and a mailbox link them.
Augment Intent
A desktop workspace for Mac, in public beta. A Coordinator agent plans, Implementor agents build in isolated worktrees, and a Verifier checks the result.
OpenHands
An open-source platform for coding agents. Its Agent Canvas control center is self-hosted and runs OpenHands, Claude Code, Codex, and other agents.
Verdent
An AI-native development environment for Mac, VS Code, and JetBrains. It runs many agents at the same time, each in its own workspace.
Cursor
Cursor's cloud agents run on Cursor's own agent loop. Workers can run on your machines. Cursor announced a deal to acquire Graphite in December 2025.
Try it on one repository for two weeks.
File a task. An agent builds it. A person reads every request. You see the cost of each task.