Beelzebub
v3.10.0 open-sourceThe section your link pointed to isn't on Beelzebub's page any more, so we've brought you to the top.
Beelzebub is an open-source deception framework that deploys realistic decoys to observe attacker behavior and capture interactions as security evidence.
beelzebub --validate
protocol: telnet
beelzebub --memLimitMiB 256
apiVersion: "v1"
protocol: "ssh"
address: ":2222"
description: "SSH LLM Honeypot"
commands:
- regex: "^(.+)$"
plugin: "LLMHoneypot"
serverVersion: "OpenSSH"
serverName: "ubuntu"
passwordRegex: "^(root|qwerty|123456|jenkins)$"
deadlineTimeoutSeconds: 60
plugin:
llmProvider: "ollama"
llmModel: "llama3"
apiVersion: "v1"
protocol: "ssh"
address: ":2222"
description: "SSH LLM Honeypot"
commands:
- regex: "^(.+)$"
plugin: "LLMHoneypot"
serverVersion: "OpenSSH"
serverName: "ubuntu"
passwordRegex: "^(root|qwerty|Smoker666|123456|jenkins|minecraft|sinus|alex|postgres|Ly123456)$"
deadlineTimeoutSeconds: 60
plugin:
llmProvider: "openai"
llmModel: "gpt4-o"
openAISecretKey: "sk-proj-123456"
Configure your service YAML to set the LLM provider to Ollama with the llama3 model, point the endpoint at your local Ollama instance (e.g. http://localhost:11434), then start Beelzebub as normal.
Summary
Beelzebub is an open-source deception runtime, free to use, that deploys decoy SSH, HTTP, TCPTCPA network protocol that delivers a reliable, ordered stream of bytes between two endpoints. It detects lost data and retransmits it., TELNET, and 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. services to engage attackers with 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.-generated responses rather than static banners. It runs as a self-hosted service, deployed via Go binary, Docker, or Helm on Kubernetes, and configured through YAML with a plugin system for extending honeypot behavior. It suits detection engineers and threat-intel teams building deception infrastructure rather than passive log-collecting honeypots, and it extends the model to modern territory by including an MCP honeypot that captures prompt injectionprompt injectionAn attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools. attempts against AI agents. The category is honeypot and deception tooling rather than a named competitor, and metrics, RabbitMQ integration, and structured logging tie it into existing SIEMSIEMSecurity information and event management, collecting logs from many systems and correlating events to find suspicious activity. Analysts use it to investigate alerts and incidents. pipelines. With 23 contributors, 93 commits in the past year, and a release 16 days ago, it is under active development.
Beelzebub is an open-source deception framework that deploys realistic decoys to observe attacker behavior and capture interactions as security evidence.
How Beelzebub helps
What is an attacker actually typing once they get past the login banner?
SSH, HTTP, TCP, and TELNET decoys pass attacker input to an LLM that generates realistic interactive responses instead of a canned prompt, and every command matched or answered is logged for review
Are AI agents on this network being targeted with prompt injection?
the MCP honeypot exposes decoy Model Context Protocol tools and scores captured interactions with an MCP Trust Score, surfacing injection attempts made against the fake tool set
Did an attacker's session survive them dropping the connection?
SSH session state is preserved after logout, so reconnections continue against the same conversation history rather than starting the deception over
Is a honeypot config safe to push before it reaches production?
configuration files can be statically checked and regular expressions are precompiled at load time, so a bad pattern or malformed definition surfaces immediately instead of failing silently once attackers connect
Can this run without sending attacker data to an external LLM provider?
the plugin configuration accepts a self-hosted model backend as an alternative to a cloud API key, letting the honeypot generate responses without an internet-facing dependency
Languages
Command line
3 commands for Beelzebub, each with where it came from. This tool has no source analysis yet, so there is no option reference and no captured run beside them.
No command matches.
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 Beelzebub, 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 Beelzebub 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…
Coverage
Missing something? Tell us
What Beelzebub connects to, runs on and detects, read from its release notes and docs. So far: 2 new detections.
2 changes, tracked since Oct 27, 2026.
-
Oct 272026
new WordPress 6.9.4 service lure
feat: add WordPress 6.9.4 service lure by @zgsec in https://github.com/beelzebub-labs/beelzebub/pull/375
-
Oct 272026
new Ollama service lure
feat: add Ollama service lure by @zgsec in https://github.com/beelzebub-labs/beelzebub/pull/374
Nothing first seen in this window. That doesn't mean Beelzebub shipped nothing, only that we found no record of it.
How we count
Read from 1 of 42 release notes and docs updates we hold for Beelzebub. "First seen" is the earliest note that names something; "last" is the latest. Our history may start partway through Beelzebub's life, so an old integration can show a recent first-seen date.
Each change counts once: "added 40 checks" is one line, so the numbers measure how often coverage moves, not how big the catalogue is or how well it detects.
Releases
42 entries
No entries match these filters.
- October 20261
- August 20262
- June 20261
- May 20262
- April 20265
- March 20261
- February 20262
- January 20261
- December 20251
- November 20251
- October 20251
- September 20251
- July 20251
- March 20255
- February 20252
- January 20252
- September 20241
- August 20242
- July 20241
- June 20242
- April 20241
- March 20241
- October 20231
- August 20231
- May 20231
- April 20231
- December 20221
Project health
Issue, contributor and maintainer activity in mariocandela/beelzebub, 2023-10 – 2026-09, as of 2026-09-25. Twelve-month figures first; the trend lines run the whole window.
- Contributors 16 +10 vs prior 12 months
- Maintainers 3 +2 joined · −1 left, last 12 months
- Bus factor 1 committers behind half the commits
- Community-filed not measured of issues opened, last 12 months
- Median time to close not measured issues closed, last 12 months
- Open backlog not measured open issues today
- Issues opened / month not measured
- Open backlog not measured
- Contributors / month 4
- Commits / month 6
- Stars 2,174
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.
Choose a badge style and copy the code →