ADR
open-sourceThe section your link pointed to isn't on ADR's page any more, so we've brought you to the top.
Enterprise cyber tool that discovers, monitors, and detects threats in AI agent activity across employee-facing and customer-facing agents.
Summary
ADR is an open-source cyber tool that monitors and evaluates the security of AI agents such as Cursor, Claude Code, and Codex, as well as customer-facing support agents. It runs as a sensor deployed alongside these agents, capturing intent, tool usetool useA model's ability to answer with a structured request to run a named function or API, which the application executes and returns. It is how agents take actions., and execution traces, paired with a detector that combines high-recall triage with deeper reasoning on suspicious sessions; a companion benchmark, ADR-Bench, tests agent defenses against over 300 tasks and 133 MCPMCPModel Context Protocol, a standard for connecting AI applications to external tools and data sources. A compatible server exposes capabilities an assistant can use through a common interface. servers covering known attack techniques. It targets security teams responsible for AI agent deployments inside organizations, sitting in the emerging agentic AI security space alongside broader observability and threat-detection tooling. Discovery and prevention components remain closed-source. The project shipped its first tracked release 21 days ago.
Enterprise cyber tool that discovers, monitors, and detects threats in AI agent activity across employee-facing and customer-facing agents.
How ADR helps
Which of my coding agents took an action nobody asked for?
the sensor captures intent, tool use, and execution traces for each session and the detector flags sessions where the action diverges from the stated intent, escalating suspicious ones to deeper reasoning
Which agent session should I actually look at first out of thousands?
the two-tier detector runs high-recall triage across all sessions and reserves deeper agentic reasoning for the subset it flags, so review time goes to the sessions most likely to be risky
Would my agent's guardrails hold up against a real prompt-injection attempt?
ADR-Bench replays over 300 tasks across 133 MCP servers covering all 17 known agent attack techniques and reports where the defenses hold and where they fail
What did this agent actually do during a support conversation before something went wrong?
the sensor reconstructs the execution trace of tool calls and intent for that session, giving a record to inspect after the fact rather than just the final output
Are my Cursor, Claude Code, and Codex agents all being watched the same way?
the sensor deploys alongside each tool and captures the same intent, tool-use, and execution-trace data across macOS, Linux, and Windows, so coverage gaps show up as agents with no captured trace
Languages
Command line
| option | found in | since | description |
|---|
Values are placeholders taken from each option’s declared default. Nothing is executed here — the output shown is a recording of a run that already happened.
Score card
-
Shipping velocity releases a month, last 12 months
-
Documentation quality release-notes rubric, 0–100
-
Breaking-change discipline how rarely a release breaks users, and notice given
-
Maintenance risk quiet time against its own cadence, maintainers
-
Innovation & surface new capabilities, API and MCP surface
- Community health
-
Contributor trend distinct committers, this year against last
-
Maintainer concentration bus factor now against a year ago
-
Issue backlog trend issues closed per issue opened, 12 months
-
Responsiveness median time to a maintainer’s first reply
Nine scores for ADR, each built from the releases, notes and API history this site tracks — and, on Researcher and Business, where it stands among every measured tool in its category and how that has moved.
Score cards are part of every paid plan.
See plans → Already subscribed? Sign in →Trajectory
Blank means never measured; nothing here is a filled-in zero.
Peer standings are included with Researcher and Business. See how this tool ranks against its competitors, using data we don't publish anywhere else.
See plans →Each score is 0–100 on a published rubric, derived from data this site already shows. A dimension we cannot measure says so — it is never scored 0 and never enters a rank.
How this is scored
- Shipping velocity — releases a month over the last 12 months, on a log scale where 16 a month scores 100. Needs 3 releases in the window.
- Documentation quality — the release-notes rubric published on the analytics page, unchanged.
- Breaking-change discipline — the share of releases carrying a breaking change (none scores 100, half or more scores 0). Only projects that label breaking changes are measured: a clean record cannot be told from an unlabelled one.
- Maintenance risk — quiet time measured against the tool's own release cadence (quiet longer than 90 days and three typical gaps scores 0), plus the number of active maintainers and whether contributors are growing, where known. Higher is lower risk.
- Innovation & surface — new capabilities in the feature ledger this year, API and MCP operations added, and the share of commits that are features: the mean of whichever we hold.
- Community health (open-source tools only) — each is a direction, not a size: contributors this year against last, the bus factor now against a year ago, and issues closed per issue opened, where steady scores 50, doubled 100 and halved 0; plus the median time to a maintainer's first reply (an hour scores about 100, a month or more 0). A commercial card has no repository and carries none of the four.
- Documented delivery (commercial tools) — when a vendor's documented new capabilities have slowed against its own baseline, that counts against the overall standing as heavily as two low dimensions. Steady delivery, or too little history to judge, leaves the standing alone; it is never a sixth score.
- Open-source tools are scored on repository signals; commercial tools on their published changelog. Ranks compare tools within one category and one profile and need at least five measured peers; the overall standing needs three ranked dimensions. Best-in-breed or consolidator is a shape, not a quality, and is never scored.
Release-note detail over time
See how much detail ADR puts in its release notes, quarter by quarter, and compare it with tracked tools in the same category. This history uses up to ten retained, reviewed notes per tool; sparse or blank older quarters may reflect that limit.
Checking release-note history…
Releases
Nothing shipped since we started watching. Releases and docs updates land here as they happen.
Project health
Issue, contributor and maintainer activity in uber/ADR, 2023-10 – 2026-09, as of 2026-09-25. Twelve-month figures first; the trend lines run the whole window.
- Contributors 18 +18 vs prior 12 months
- Maintainers 5 +5 joined · −0 left, last 12 months
- Bus factor 2 committers behind half the commits
- Community-filed 100% of issues opened, last 12 months
- Median time to close < 1 day first maintainer reply 23 hours
- Open backlog 1 of 16 issues ever filed
- Issues opened / month 1 · 0 communitymaintainers
- Open backlog 1
- Contributors / month 11
- Commits / month 21
- Stars 1,575
- other 100%
Counts from the project's public repository and git history; no individuals are identified. Maintainers are the committers covering 80% of the last year's commits. how we measure this
Add the badge to your README
Maintain this project? The badge links readers straight to this page, so they can follow every release here.
Choose a badge style and copy the code →