Deep Agents Code
LangChain · Available on HarnessRouter
An open-source terminal coding agent built on the Deep Agents SDK that works with any tool-calling model, with persistent memory, customizable skills, subagents, and approval controls.
30-day usageOct 12–Nov 10, 2026
Data as of November 11, 2026 · About the data
- Rank
- #31 #21 of 21 CLI agents · 7-day #29
- Tokens
- 5.6B
- Requests
- 68.4K
Capabilities and verification
Reviewed against the HarnessRouter capability catalog on October 26, 2026. Every verified row cites its public source; rule-derived rows apply HarnessRouter's published classification rules to documented behavior. A “No public evidence” badge marks a gap in the public record, not a statement that Deep Agents Code lacks them.
Configuration & support
- Other modelsDirectly verified
- Custom instructionsDirectly verified
- SkillsDirectly verified
- Custom toolsNo public evidence
- MCPDirectly verified
- Sandbox & approvalsDirectly verified
- SessionsDirectly verified
- SubagentsDirectly verified
Execution & agency
- Workspace filesDirectly verified
- Structured actionsDirectly verified
Environment control
- Browser controlNo public evidence
- Computer controlNo public evidence
Observation & capture
- Screen observationNo public evidence
- Screenshot exportNo public evidence
- Recording exportNo public evidence
Artifact outputs
- DocumentsRule-derived
- SpreadsheetsRule-derived
- PresentationsRule-derived
- ImagesRule-derived
- VideoRule-derived
- App deploymentNo public evidence
Sources: docs.langchain.com
Machine interfaces
Headless CLI · StableACP server · StableSDK · Stable
Run Deep Agents Code through HarnessRouter
harness_iddcode
Use it for coding-agent tasks returned through the HarnessRouter product contract.
Create an API key and run your first task ›Run a taskHarnesses API
Run Deep Agents Code through one API.
Ship it behind your product and compare it on your own tasks. Start free with your own model keys, no card needed.
Start building free