JavaScript · MIT
pguso/ai-agents-from-scratch
Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.
★ 4.9k
Stars
712 forks · 12 open issues
+2.4/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
29.2
Momentum / 100
see the breakdown below
12mo ago
Created
last push 3mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 10.2 | +2.4/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 1.9 | last week ran 1.13× the monthly pace |
| Freshness | 15 | 6.4 | last push 3mo ago; decays to zero at 180 days |
| Scale | 15 | 10.7 | 4.9k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 29.2 | sum of the above |
Detail
| Topics | ai-agentseducationalfunction-callingllmllm-agentnode-llama-cppreact-agenttutorial |
| Matched on | AI Agents (llm-agent) Agent Skills & MCP (function-calling) LLM & Inference (llm) Learning & Roadmaps (tutorial) |
| Short window | +17 stars over 7 days = 2.4/day |
| Long window | +56 stars over 26 days = 2.2/day |
| Lifetime average | 12.97 stars/day over 378 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |