Runtime verification for Cursor, Claude Desktop, Claude Code, Codex, OpenClaw, and Hermes
Your developers and contractors run Cursor, Claude Desktop, Claude Code, Codex, OpenClaw and Hermes on their machines and servers, with access to files, shells, credentials and MCP tools. EDAMAME, the AI agent trust layer, watches each agent from outside the agent, with no plugin or SDK inside it, and turns what it sees into evidence and access decisions.
Judge each agent by what it did, not by what it said.
EDAMAME compares what an agent was asked to do with what the machine actually saw, from outside the agent.

Reads the declared task
EDAMAME reads each agent's transcripts on the host: the task it was given and the tools it called.
Watches the machine, not the chat
Processes, files and network, read from the operating system, outside the agent's own process.
Scores the gap
A divergence verdict with its evidence, and no plugin to install inside the agent.
Caught by technique, not by indicator.
The same host telemetry catches compromised behavior: what code opens, spawns and sends.

Eleven deterministic checks
Such as token exfiltration, credential harvest, sensitive-material egress, sandbox escape and file tampering, plus an agent turning its own sandbox off or re-spelling a denied command.
Release-gated
Each release must pass 23 attack scenarios and a divergence scenario on four platforms, plus a ten-minute idle window with zero findings. These are release tests, not a measured false-positive rate in production.
Known attacks, caught as behavior
EDAMAME has flagged the axios npm RAT, the tj-actions/changed-files compromise and the litellm PyPI takeover. Of the 12 publicly documented incidents in our September 2026 threat-coverage review, 11 exercise a technique it already detects.
Deterministic, no model needed
These detectors run on the device, with no data leaving the machine. A new indicator arrives as a signed threat model, with no app update. A model adds intent reading and explanations, as the table below shows.
The attack scenarios are public: test triggers on GitHub
Detection runs without a model. A model adds intent and explanations.
A model is optional. It reads each agent's transcripts to predict its intent for the divergence check, reduces noise and explains findings.
| Capability | What it does | Needs a model |
|---|---|---|
| AI agent discovery | Finds the agents, MCP servers and harnesses on the device | No |
| Posture checks | Scores the device against the threat models | No |
| Traffic anomaly detection | Flags unusual network behavior per process | No |
| Attack-pattern detection | Credential harvest, token exfiltration and the other deterministic checks | No |
| Intent divergence | Compares what the agent declared with what the machine did | Partly. A deterministic check runs without one; a model reads the transcripts to predict intent and refine the verdict |
| Noise reduction | Adjudicates context on findings | Yes. It can never clear a corroborated critical finding |
| Explanations and fixes | The AI Security Assistant explains findings and proposes remediation | Yes |
| Access decisions | EDAMAME Hub applies your policy to the reported posture | No |
Model choices: EDAMAME's managed AI service in EDAMAME Portal (free tier included), your own Claude or OpenAI key, or a local model through Ollama.
The agents you already run, observed as they are.

Found from their transcripts
Agents are discovered from their transcript folders on disk: nothing to install for them to be seen.
What each one can reach
MCP servers, tools and secrets, and the agents that run unsandboxed, with passwordless root, or drive critical subprocesses.
Harness coverage
EDAMAME detects the sandbox or harness you already run and flags the agents running without one.
An observer the agent does not control
An agent cannot dismiss a finding or switch detection off: those actions stay with the operator, and a paused observer is itself reported.
What the observer assumes.
Beside the agent, not inside it
EDAMAME reads processes, files and network from the operating system, outside the agent's own process, with no plugin inside the agent. On macOS this runs through the EDAMAME Helper, a system service.
The operator keeps the verdicts
Dismissing a finding, switching detection off and pausing the observer stay with the operator, not the agent.
A paused observer is reported
An agent on the machine whose observer is paused raises an unsecured-agent finding, and EDAMAME Hub shows it on the device's AI posture.
Coverage follows the host
EDAMAME observes the agents that run on its own machine. For an agent in a VM, a container or on a remote server, run EDAMAME Posture there.
Silence is visible
A device that stops reporting is escalated in EDAMAME Hub as signal lost.
Administrator rights are the line
The observer assumes the agent does not hold administrator or root rights. EDAMAME flags agents that can get root without a password, with the fix.
The same proof on runners, build hosts and agent servers.
EDAMAME Posture is the CLI for CI/CD runners and any server running AI agents, cloud or self-hosted, such as an OpenClaw or Hermes host.

Posture before secrets
Patch, firewall, encryption and remote-access checks on the runner, before it touches a repository or a secret.
Egress allow lists
Each outbound connection is checked against the runner's allow list. A violation fails the build, and with cancel-on-violation it can stop the pipeline while it runs.
In your pipeline
Run it as a CLI, or in GitHub Actions with the EDAMAME Posture action.
A critical finding takes the host out of your access lists.

Policies on posture and agents
A critical finding or a divergence verdict lowers the device score, so the host stops meeting your EDAMAME Hub policy.
Access follows the policy
When the host falls out of policy, EDAMAME Hub updates your access control (GitHub, GitLab, Microsoft Entra ID, Google, Tailscale, NetBird, Netskope or FortiGate), and that provider enforces it.
Fixed, back in
Once the issue is resolved, the device meets the policy again and gets its access back.
Mapped to the frameworks
Every AI check carries its OWASP Agentic, OWASP LLM, MITRE ATLAS and ISO/IEC 42001 references.
“Signed, allow-listed AI CLIs and runtimes become ‘living-off-the-AI’ tooling”
Microsoft adds that detection depends on “establishing what normal looks like for each agent [...] so that deviation becomes visible.” Source: Microsoft Digital Defense Report 2026, pp. 16–17.


