What Tablif read on Agenturm's site
Agenturm describes itself as: “Agenturm — Know what your agents are doing skip to content agenturm .dev Demo Integrations Install Docs ↗ GitHub ↗”
- Stage: Live, no waitlist
What it is
Calls itself “Local observability for coding agents”.
- Calls itself: Local observability for coding agents
“Local observability for coding agents”
Where it puts itself
Rules out “Agenturm does not take over your agent sessions.”.
- Says it will not: Agenturm does not take over your agent sessions.
“Agenturm does not take over your agent sessions.”
What it costs
No free plan.
- Free plan: no
“Do I need an account, an API key, or a subscription? + No account or provider key is needed for local monitoring and recorded-progress summaries. Agenturm is open source under the MIT license.”
Who it sells to
Sells to developers.
- Sells to: developers
“Local observability for coding agents”
How it runs
Runs on Linux, Windows and macOS. Runs locally and works offline. Open source. AI is a side feature. You can bring your own API key.
- Runs on: Linux · Windows · macOS
- Runs where: on the device, offline
- Open source: yes
- AI role: a side feature
- Bring your own key: yes
“Requires Python 3.11+, Git, and uv. Works on macOS, Linux, and Windows.”
“Your data stays on your machine; replies and approvals stay in your hands”
What it works with
Integrates with Claude Code, Codex, Gemini CLI and 4 more.
- Integrates with: Claude Code · Codex · Gemini CLI · +4
“Agenturm brings your agents’ sessions, activity, tool calls, and traces into one local terminal view.”
“Works with Codex, Claude Code, OpenCode, Pi, and other agents.”
What it offers as proof
Live, no waitlist. Publishes docs.
“No account required”
“Docs ↗ -> https://github.com/abhishekash/agenturm/blob/main/docs/usage.md”
Sources
Tablif read these pages, last on 28 Oct 2026. Everything above is what the product says about itself; Tablif does not verify every claim.
Similar products in Tablif Town
- Agentic Workbench: Supervised coding agents with reviewable changes
- Agent Activity: See what your AI agents do behind
- Agents At Work: You can go!: Your coding agents on your phone, with an open-source engine
- AgenticWebTeam: Your website, run by an AI team that does the work
- Craft Agents: The world's most powerful agents, with the UX they deserve
- Agent V: Agent V is a desktop coding agent.
- Agent Middleware: Permits and signed receipts for AI agent tool calls
- Terminalblog.com: Tracking the AI coding agent ecosystem