Abstractor.io
agentflow a sub-product of Abstractor v1.8.0

Run your Claude Code fleet. Monitor everything. Trust nothing without a policy.

agentflow is the missing control plane for Claude Code agent fleets — live monitoring, per-tool policy enforcement, and sub-agent orchestration from a single self-hosted binary.

Orchestrate with oversight.

Your keys, your machine Single self-hosted binary Closed-source, never phoning home
What the fleet looks like from the dashboard
agentflow hub — session: Claude — v1.8.0
  AGENT                      STATUS       TOKENS     COST      STALL
  ──────────────────────────────────────────────────────────────────
  orchestrator-agent         ● running     5.2k tok   $0.078    —
  developer-agent            ● running    12.1k tok   $0.182    —
  abstractor-dev-agent       ✓ done        8.4k tok   $0.126    —
  test-agent                 ⏸ waiting        —          —    → dev-agent
  web-agent                  ● running     3.7k tok   $0.056    —
  ──────────────────────────────────────────────────────────────────
  5 panes  ·  29.4k tok  ·  $0.442  ·  refeed: ON  ·  ⚡ 4 tools blocked
● LIVE SSE stream /dispatch · /stats · /stalls Wake · Send Continue · Kill REPL
Two more views into the same fleet
Pane grid 8 of 24 shown
orchestrator-agent
running
5.2k tok · $0.078
developer-agent
running
12.1k tok · $0.182
abstractor-dev-agent
done
8.4k tok · $0.126
test-agent
waiting
— tok · —
web-agent
running
3.7k tok · $0.056
borz-language-dev-agent
running
9.8k tok · $0.147
ephernity-dev-agent
stalled
— tok · —
management-agent
idle
1.1k tok · $0.016
Handoff graph 1 stalled
screenshots compile-stub verify stalled web-agent borz-language-dev-agent test-agent abstractor-dev-agent ephernity-dev-agent management-agent
Edges shown are real dependencies from a running agentflow fleet.

What ships in v1.8.0

Six capabilities that close the gap between "agents are running somewhere" and "I know exactly what they are doing and why."

Multi-instance hub

agentflow hub serve federates multiple machines into a single dashboard. Route sub-fleets to different hosts; the hub aggregates status, handoff graph, and stall conditions across all connected nodes from one URL.

Dashboard v1.6 — live fleet monitoring

Browser-based monitoring with dedicated /dispatch, /stats, and /stalls endpoints. HTMX SSE badges update per-pane in real time. The /stats view shows real-time weekly quota via OAuth credit probe — credit headroom visible without leaving the dashboard.

Per-tool policy enforcement

A PreToolUse hook gates every Bash, Read, Write, and Edit call against a YAML deny list before the agent acts. Auto-approve trusted read-only operations; surface anything outside policy to the operator for review.

Handoff graph + stall detection

Server-rendered SVG shows the live agent dependency graph — who is waiting on whom. The stall dashboard surfaces blocked agents and their wait conditions. Stalled agents recover via local Ollama (gemma4:12b) — no cloud call required.

Auto-refeed loop

agentflow supervise --refeed automatically continues stalled agents after a configurable dwell. The night-mode master switch pauses the loop on demand — agents hold until the operator resumes the refeed.

Sub-agent spawning with inherited permissions

Spawn scoped Claude Code sub-agents from the orchestrator. Each inherits the parent's deny scope via a derived policy file. Sub-agent panes are auto-registered with the approve-watcher — no manual wiring.

Self-hosted in three steps

Your Anthropic API key never leaves your machine. Neither does the fleet state, the session logs, or the DISPATCH-LOG audit records.

01

Drop the binary

Copy agentflow to your PATH. One file, no runtime, no Docker. Works wherever Claude Code runs.

cp agentflow /usr/local/bin/
agentflow serve --port 7070
02

Write your YAML policy

Declare which tool calls require approval and which are auto-allowed. Rules are inherited by every sub-agent your fleet spawns.

deny:
  - pattern: rm -rf*
  - pattern: git push --force
allow_readonly: true
03

Open the dashboard

Navigate to localhost:7070. Live SSE badges, action buttons, the handoff graph, and the stall dashboard are waiting.

open http://localhost:7070/
#  session: Claude
#  5 panes · 4 tools blocked today
Stack

Go net/http · HTMX · Server-sent events · Server-rendered SVG · Zero external JS frameworks · Single static binary

External deps

none at runtime

Early access

Know what your agents are doing.

agentflow is in private beta. If you're running Claude Code agents in production and want visibility, policy enforcement, and a handoff graph — reach out.

Closed-source. Self-hosted. Your keys never leave your machine.