AI agent
awesome-agent-architecture
Curated architecture notes and system reviews of modern AI agents.
- Rank
- #759 of 2,525
- Stars
- 194★ +5/wk
- On radar
- since 2026-07-15
Momentum
rate of rise, not size · recomputes hourly
51.7
24h· new7d· new
Collecting daily history; the trend chart appears after 3 days on the radar
Why it's ranked
awesome-agent-architecture is an AI agent ranked #759 of 2,525 on the Cresting momentum radar, with a score of 51.7. It has 194 GitHub stars, +5 in the last 7 days, and has been tracked since 2026-07-15.
Every score decomposes into published factors, the same math for every tool, paid or not. Read the methodology →
| Velocity (weighted, cohort-normalized) | 0.768 |
| Recency boost | 0.194 |
| Signal decay | 0.994 |
| Corroboration | 1.000 |
| Quality gate | 1.000 |
Raw signals (30 days)
github · forks+0 in window · 25 latest · 2 snapshots
github · stars+5 in window · 194 latest · 2 snapshots
Related ai agents
- blitzosBlitzOS — Claude/Codex Cloud VMs that boot knowing your whole codebase#1 · 108★
- codex-model-routing-teamRoute complex Codex tasks to model-specific background workers with bounded concurrency and lead-agent verification.#2 · 134★
- 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.#5 · 1,113★
- waggleAttributed, resolvable artifact references for agent handoffs — a ~30-byte token instead of pasted context. MCP-native; the reference layer for the agent-harness world.#7 · 743★
- clawkDisposable, network-restricted Linux VMs for AI coding agents#10 · 537★