crust
v4.4.0 open-sourceThe section your link pointed to isn't on crust's page any more, so we've brought you to the top.
Crust is a transparent, local gateway between AI agents and LLMLLMA large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. providers that intercepts tool calls and blocks dangerous actions before they execute.
curl http://localhost:8080/api/security/plugins crust agents crust doctor agent scan crust mcp crust mcp-discover crust mcp-http crust acp-wrap --agent goose crust doctor --report crust --foreground --listen-address 0.0.0.0 curl --unix-socket ~/.crust/crust-api-8080.sock http://localhost/api/telemetry/sessions crust status --live crust extract --tools web_search,browser agentshepherd start
Summary
crust is an open-source gateway, licensed under Elastic License 2.0, that sits between AI agents and LLM providers and blocks dangerous tool calls — file reads, shell commands, network requests — before they execute. It runs as a local command-line install (a single script sets up the proxy), acting as a transparent gateway rather than a hosted service, and the vendor stresses that data never leaves the machine. It's aimed at teams building or operating AI agents who need runtime guardrails against destructive or unauthorized actions, wrapping 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. or ACP agents directly with no code changes. A paid Crust Pro tier exists for enterprise features, but the core gateway is free to run yourself. With 6 contributors, 435 commits and 10 releases in the past year, and a first commit in 2026, it's an active, very young project.
Crust is a transparent, local gateway between AI agents and LLM providers that intercepts tool calls and blocks dangerous actions before they execute.
How crust helps
Which shell commands is an agent about to run before they hit my system?
intercepts every tool call at the gateway and blocks the ones matching destructive or unauthorized patterns before they execute, so the command never reaches the shell
Which file reads should an agent never be allowed to make?
sits transparently between the agent and the LLM provider and stops file-read tool calls that match its rules, without requiring any change to the agent's code
Is an agent already wrapped and protected right now?
reports which running agents are detected and their current protection status, so you can confirm a given agent isn't running unguarded
What did an agent actually try to do during a session?
follows live activity logs of every tool call passing through the gateway, giving a real-time record of what was requested and what was blocked
Can I stop a new kind of dangerous call without restarting everything?
lets you add custom rules that hot-reload into the running gateway, so newly written checks take effect without dropping the current session
Does my agent's traffic ever leave my machine?
runs entirely as a local proxy between the agent and the LLM provider, so tool-call interception and blocking happen on-machine rather than through a hosted service
Languages
Command line
No command matches.
| 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 crust, 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 crust 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
17 entries
No entries match these filters.
- March 20268
- February 20269
Project health
Issue, contributor and maintainer activity in BakeLens/crust, 2023-10 – 2026-09, as of 2026-09-25. Twelve-month figures first; the trend lines run the whole window.
- Contributors 4 +4 vs prior 12 months
- Maintainers 1 +1 joined · −0 left, last 12 months
- Bus factor 1 committers behind half the commits
- Community-filed 100% of issues opened, last 12 months
- Median time to close 1.7 days first maintainer reply 11 hours
- Open backlog 0 of 7 issues ever filed
- Issues opened / month 0 · 0 communitymaintainers
- Open backlog 0
- Contributors / month 0
- Commits / month 0
- Stars 439
- bugs 29%
- features 43%
- other 28%
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
Libraries its release ships
What its latest release locks, checked against known advisories.None of its release's images build from a lockfile we can read.
Add the badge to your README
Maintain this project? The badge links readers straight to this page, so they can follow every release here.