ArchonvsMicrosoft Conductor
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Archon
Cole Medin · Agent harness
OSS
Panel
7.12 spec wins
- Reliability
- 6.8
- Usefulness
- 7.0
- Cost
- 8.7
- Longevity
- 6.0
“You can dispatch a production workflow from Telegram, which is either operational maturity or a cry for help.”
Microsoft Conductor
Microsoft · Agent harness
OSS
Panel
7.01 spec wins
- Reliability
- 7.0
- Usefulness
- 6.0
- Cost
- 8.7
- Longevity
- 6.3
“There is another Conductor on this board from a different company, which is what happens when nobody owns the word.”
Spec by spec
| Spec | Archon | Microsoft Conductor |
|---|---|---|
| Architecture | ||
| Category | Agent harness | Agent harness |
| Runs | local | local, sandbox |
| Platforms | macos, linux | macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | No |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | No |
| Browser control | No | No |
| Sandboxed execution | No | YesAzure Container Apps sandboxed execution is offered as an experimental provider. |
| Multi-agent orchestration | Yes | Yes |
| Headless / CI mode | Yes | YesWorkflows are plain YAML intended to run the same way locally and in CI, with terminate steps mapped to CLI exit codes. |
| Models | ||
| Backbone | any | GitHub Copilot SDK, Anthropic Claude, Claude Agent SDK (experimental), NousResearch Hermes (experimental) |
| Bring your own model | Yes | Yes |
| Local models | No | No |
| Cost | ||
| Pricing model | free | byok |
| Starts at | n/a | $0/mo |
| Free tier | Yes | Yes |
| Bring your own key | Yes | Yes |
| Openness | ||
| Open source | Yes | Yes |
| License | MIT | MIT |
| GitHub stars | 23,599 | 465 |
Which one would each critic pick
| Critic | Archon | Microsoft Conductor | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.3 | 7.0 | Archon — Pick Archon if you want work started from a GitHub comment and finished as a pull request; pick Conductor or Claude Squad if writing a workflow file before the first run sounds like the wrong order. |
| El Crítico | 6.8 | 6.5 | Archon — Isolation is a git worktree, which separates file trees and nothing else, so parallel runs share one machine, one network and one set of credentials. |
| El Profesor | 7.3 | 7.5 | Microsoft Conductor — Control flow is evaluated outside the model, so identical inputs traverse an identical path and no tokens are consumed deciding what executes next. |
| La Inversora | 6.8 | 6.8 | no preference |
| La Jefa | 6.5 | 6.8 | Microsoft Conductor — Nothing per seat across sixty desks, terminate steps map to CLI exit codes so it gates in a pipeline, and there is no console, no SSO and no audit trail. |
| El Hacker | 8.3 | 7.5 | Archon — MIT, the whole process is YAML in .archon/workflows that lives in the repo, and the AI node swaps between Claude Code and Codex without touching anything else. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.