reflectt-node in 5 minutes: from zero to coordinated AI agents

Source: Dev.to

Step 1: Install reflectt-node (≈ 60 seconds)

curl -fsSL https://www.reflectt.ai/install.sh | bash

This installs the reflectt binary and starts the local server at http://localhost:4445. No Docker required.

Verify it’s running:

curl http://localhost:4445/health

You should see {"status":"ok"}.

Step 2: Create your first task (≈ 30 seconds)

curl -X POST http://localhost:4445/tasks \
  -H 'Content-Type: application/json' \
  -d '{
    "title": "Write a README for my project",
    "assignee": "unassigned",
    "priority": "P2",
    "done_criteria": ["README covers installation, usage, and contributing"]
  }'

Copy the task ID from the response.

Step 3: Connect an agent (≈ 2 minutes)

Pick any agent you’re already running. Below is the pattern for Claude Code:

claude --print "You are an agent connected to a task board at http://localhost:4445.

Pull your next task:
curl http://localhost:4445/tasks/next?agent=claude

Claim it:
curl -X PATCH http://localhost:4445/tasks/ \
  -d '{\"status\":\"doing\",\"assignee\":\"claude\"}'

Post progress updates to the task as comments:
curl -X POST http://localhost:4445/tasks//comments \
  -d '{\"author\":\"claude\",\"content\":\"Working on intro section\"}'

When done, move to validating:
curl -X PATCH http://localhost:4445/tasks/ \
  -d '{\"status\":\"validating\"}'

Now pull and complete the task: $TASK_DESCRIPTION" \
  --permission-mode bypassPermissions

The same pattern works for Codex, OpenClaw, or any agent that can make HTTP requests.

Step 4: Add a second agent (≈ 1 minute)

The value is in coordination. Add another agent with a different name:

curl http://localhost:4445/tasks/next?agent=codex

Each agent claims tasks exclusively, can see each other’s claimed tasks, and avoids collisions.

What you have now

• A local task board that agents can read and write.
• WIP‑limited parallel execution — agents can work simultaneously without stepping on each other.
• An audit trail of what each agent did and when.

The full reflectt-node feature set (presence, structured chat lanes, reviewer routing, cost tracking) builds on this foundation, but the above is enough to get started.

Common gotchas

“The server stopped after I closed my terminal.”
Run reflectt start --daemon to keep it running in the background.

“My agent can’t reach localhost:4445.”
If the agent runs in a container or remote environment, replace localhost with your machine’s IP address or set up a tunnel.

“I want multiple agents to work on the same codebase without conflicts.”
That’s the point. Each agent claims one task at a time. If tasks are scoped correctly (e.g., one task per file or feature area), conflicts are rare by design.

What’s next

• How we coordinate 21 agents on one codebase — the full architecture.
• The 3 failure modes we hit — what breaks without coordination.
• reflectt-node on GitHub — source, issues, full docs.