AI agent
agent-spec
`agent-spec` is an AI-native BDD/spec verification tool for task execution.
- Rank
- #946 of 2,565
- Stars
- 420★ +11/wk
- On radar
- since 2026-07-18
Momentum
rate of rise, not size · recomputes hourly
49.2
24h· new7d· new
Collecting daily history; the trend chart appears after 3 days on the radar
Why it's ranked
agent-spec is an AI agent ranked #946 of 2,565 on the Cresting momentum radar, with a score of 49.2. It has 420 GitHub stars, +11 in the last 7 days, and has been tracked since 2026-07-18.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.832 |
| Recency boost | 0.000 |
| Signal decay | 0.987 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+2 in window · 31 latest · 2 snapshots
github · stars+11 in window · 420 latest · 2 snapshots
Related ai agents
- klaatcodeOpen-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.#2 · 140★
- deja-vuMemory layer for coding agents: search, MCP recall, auto-context, secret redaction, stats, share and sync over the session logs Claude Code, Codex and opencode already write. One zero-dep binary.#4 · 366★
- skillsOpen-source OpenAI Codex theming Skill, AI theme generator, and cross-platform runtime for custom Codex desktop themes.#5 · 194★
- clodex-ideLocal-first, zero-trust agentic IDE for verifiable autonomous software development.#7 · 840★
- 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。#8 · 1,092★