Plan deliberately.Build in parallel.

usebdfl.com · 2026-07-23 · by Long Nguyen ·generic
BDFL is a terminal supervisor for Codex, Claude Code, and Ollama-backed Codex sessions. Plan deliberately, build in parallel, and stay in control.

Plan deliberately.Build in parallel.

Benevolent Delegator for LLMs

Plan deliberately.

Build in parallel.

BDFL is a terminal supervisor for AI agents. Create versioned plans, review diffs, approve whole plans or individual sections, delegate work to isolated workers, review every result, and stay in control.

Get BDFL ↓ View source

`$ npm install --global @thisisnsh/bdfl`

P Planner

1 Worker

2 Worker

Review

01 approve plan

02 parallel execution

03 verify & integrate

One supervisor. Your choice of agents. More coming soon.

CODEXCLAUDE CODEOLLAMA (VIA CODEX)

01 / THE IDEA

Multiple agents.

One supervised workflow.

Use Codex, Claude Code, or Ollama independently for planning and worker roles. Work with a planning agent, compare and approve versioned plans or individual sections, then let isolated worker agents implement the approved work.

02 / IN THE TERMINAL

Multiple agents.

Every session in view.

Manage running sessions or resume closed ones. Navigate to any worker from the bottom rail to follow progress or respond when it needs attention.

bdfl — terminal supervisor

bdfl 0.1.0

\[New\] \[Sessions\] \[Plans\] \[Review\]

\[Codex 1\] (W 1) (W 2\*) \[Claude Code 1\] (W 3✓)

↗ This demo is live. Click the top actions and agent rail.

03 / WORKFLOW

Complete Workflow

Role-specific `bdfl` MCP tools and the `bdfl-plan` skill keep planning and verification read-only while workers edit only isolated worktrees.

01

Talk

Work with a planning agent that can inspect the repository but cannot edit it.

02

Plan

Define shared decisions, owned paths, dependencies, locks, local checks, and global validation.

03

Review

Review plan versions, compare diffs, and request revisions where needed.

04

Approve

Approve exact sections. Execution stays blocked until every section is approved.

05

Build

Build eligible chunks in isolated branches and worktrees where the dependency graph allows.

06

Review

Review each worker’s actual diff and checks. Accept it or send feedback.

07

Verify

Verify the consolidated result with global checks and a fresh non-implementing agent.

08

Integrate

Integrate only after final review while the frozen target remains unchanged and clean.

04 / CONTROL SURFACE

Supervised from plan to integration.

Role-specific `bdfl` MCP tools constrain each agent: planners and verifiers do not edit; workers edit only isolated worktrees.

01

Deliberate & versioned planning

Browse durable plan versions, compare adjacent versions, inspect exact changes, and approve individual sections while preserving unchanged approvals.

v01

→

v02approved

02

_P_123

Multiple agents & parallel sessions

Use Codex, Claude Code, or Ollama independently for planning and worker roles, with separate models, effort levels, and options.

03

main_→worktree/1→_review

DAG-based isolated execution

Each worker receives isolated, focused context. Independent chunks run in parallel while prerequisites and named locks keep conflicting work in order.

04

✓ unit tests_✓ global checks✓_ fresh verification

Review before integration

Inspect each worker’s summary, diff, changed paths, checks, and commit metadata. Accept the result or send feedback to the same worker.

05

Local state and safety

Each repository owns its ignored `.bdfl/` runtime state. BDFL does not publish local state, metrics, analytics, or logs; use Ollama with a local model for a fully local setup.

Read the permissions model →

LOCAL

05 / GET STARTED

Plan deliberately.

Build in parallel.

Install globally, start BDFL in a Git repository, then choose separate planning and worker agents, models, effort levels, options, and worker capacity.

`$ npm install --global @thisisnsh/bdfl` Copy

Requires macOS or Linux, Node.js 20+, Git, and at least one supported agent CLI installed and authenticated.

usebdfl.com · 6 links

Comments (0)

No comments yet