AI agent
mantis
A modular, stack-agnostic toolkit of security review skills for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.
- Rank
- #452 of 2,506
- Stars
- 205★ +18/wk
- On radar
- since 2026-07-14
Momentum
rate of rise, not size · recomputes hourly
55.5
24h· new7d· new
Collecting daily history; the trend chart appears after 3 days on the radar
Why it's ranked
mantis is an AI agent ranked #452 of 2,506 on the Cresting momentum radar, with a score of 55.5. It has 205 GitHub stars, +18 in the last 7 days, and has been tracked since 2026-07-14.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.859 |
| Recency boost | 0.124 |
| Signal decay | 0.995 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+4 in window · 26 latest · 2 snapshots
github · stars+18 in window · 205 latest · 2 snapshots
Related ai agents
- clodex-ideLocal-first, zero-trust agentic IDE for verifiable autonomous software development.#1 · 801★
- WorkBuddyGuideA practical, open-source guide to mastering WorkBuddy through real-world workflows.开源的 WorkBuddy 实战蓝皮书：教程、真实工作流、Skills、MCP、自动化与多智能体实践。#3 · 681★
- fable-methodThe Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.#4 · 708★
- loop.jsA loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.#5 · 110★
- pilotfishMulti-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.#6 · 450★