AI agent
agentbehavior
Standards for defining and evaluating agent behavior
- Rank
- #951 of 2,806
- Stars
- 124★ +9/wk
- On radar
- since 2026-07-30
Momentum
rate of rise, not size · recomputes hourly
49.8
24h· new7d· new
Collecting daily history; the trend chart appears after 3 days on the radar
Why it's ranked
agentbehavior is an AI agent ranked #951 of 2,806 on the Cresting momentum radar, with a score of 49.8. It has 124 GitHub stars, +9 in the last 7 days, and has been tracked since 2026-07-30.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.822 |
| Recency boost | 0.024 |
| Signal decay | 0.994 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+0 in window · 2 latest · 2 snapshots
github · stars+9 in window · 124 latest · 2 snapshots
Related ai agents
- qwen-audio-agentA realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents#2 · 447★
- openclaude-improvedruns anywhere. uses anything#4 · 562★
- deer-workflowAn open-source Dynamic Workflow runtime that keeps orchestration in TypeScript and delegates semantic work to replaceable Agent runtimes.#5 · 357★
- cindyConsider it done. The open-source AI agent that works out of the box · 想到，就能做到。开源、开箱即用的 AI Agent。#7 · 1,170★
- numbatVisibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.#8 · 380★