Build Your Own Agent Platform
Frameworks and extensible platforms used to assemble custom agents, tools, sandboxes, and orchestration.
Comparison held
No “best” claim yet.
This collection needs at least 2 eligible repositories with reviewed canonical results. Candidates remain visible for planning, but they are not ranked and no missing score is estimated.
| Candidate | Evidence | Functional fit | Required authority | Data sensitivity | Operator burden |
|---|---|---|---|---|---|
| DeepSeek HarnessRepository ↗ | No reviewed result | coreDeveloper-preview harness with high attention; exact commit and defaults still require static review. | Plugin runtime, tools, permissions, and deployment infrastructure | Prompts, workspace data, credentials, and infrastructure data | high |
| DeerFlowRepository ↗ | No reviewed result | coreExtensible platform with explicit orchestration and sandbox choices. | Sub-agents, browser, sandbox, and research tools | Workspace, retrieved content, and generated artifacts | high |
| OpenHandsRepository ↗ | No reviewed result | coreMature platform with auditable isolation and permission decisions. | Sandbox, shell, browser, repository, and integrations | Source code, task data, and credentials | high |
Campaign rationale
Foundation choices create durable security consequences before application controls exist.
What this page does not claim
Membership, stars, forks, discussion volume, and functional fit do not change a repository’s static score or assurance level.
Workflow boundary
A complete stack earns no workflow label until its exact components, permissions, prompts, tools, environment, and scenarios have been assessed together.