agmsg
Cross-vendor messaging for CLI AI coding agents, let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no daemon, no framework.
Runssource: GitHubhomepageShellMITcommit f5a72deb477e
Shell, MIT licensed. The project labels itself: agent communication, agent teams, agentic, ai agents, bash, claude code, cli and codex.
agmsg runs. An Argusic agent installed it in 2 minutes and hit 3 errors on a clean machine with no GPU, and the whole session was recorded.
agmsg installed to ~/.agents/skills/agmsg/ (version f5a72de), sends/inboxes/history work correctly between 2 agents on the same team through SQLite store, and the test suite runs with all core functional tests passing.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 93.3 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- sqlite3 CLI binary not on system PATH2 minutes
- bats test runner not installed1 minute
- test_node_resolve.bats test 2 fails - NVM version-manager node path detection fails in container without NVM
- Install time
- 2 minutes
- Cold machine to finish
- 20 minutes
- Errors hit and fixed
- 3 hit, 2 fixed with no human help
- How the result was proved
- End-to-end test: bash scripts/join.sh created team e2e-v2 with agents agent-alpha and agent-beta; scripts/send.sh delivered messages between them; scripts/inbox.sh showed each agent received 1 message; scripts/history.sh showed both messages; sqlite3 messages.db confirmed 6 event rows including both messages. Test suite: all 26+ core .bats files passed individually (200+ tests) with only 1 failure in test_node_resolve.bats (NVM not present in container).
- Model tokens used
- 130,617
- Exact commit tested
- f5a72deb477e
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
3. test_node_resolve.bats test 2 failure - unix path mismatch for NVM version-manager node detectio… Verification: end-to-end messaging between 2 agents works; all test suites pass (except 1 NVM test) Now I have all the data. Let me compile the final structured exec /bin/sh -lc '# Final precise time check echo "Started deploy at ~10:15, install done by ~10:17, tests running from ~10:17-10:35" echo "Install took ~2 minutes, total session ~20 minutes"' in /work/repo succeeded in 0ms: Started deploy at ~10:15, install done by ~10:17, tests running from ~10:17-10:35 Install took ~2 minutes, total session ~20 minutes tokens used 130,617
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 2 minutes.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Hit 3 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 2 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agent-communicationagent-teamsagenticai-agentsbashclaude-codeclicodexcopilotdeveloper-toolsgemini-cliinter-agentmulti-agentsqlite
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agmsg)Questions
- Does agmsg run?
- Yes. agmsg runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test agmsg?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit f5a72deb477e. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test agmsg?
- The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agmsg take to install?
- 2 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does agmsg need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agmsg?
- 3 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for agmsg?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.