Skip to content

pguso/ai-agents-from-scratch

View on GitHub ↗Related repositories →

Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.

active 2025-10-232026-07-02 (UTC)

Partial coverage11,215 / 11,907 hourly files (94%) · 2 absent upstream · 690 failed, retryable2025-04-012026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
1.5K
Pushes
31
Pull requests
2
Issues
24
Stars
1.3K
Forks
118

Activity over time

Daily event counts in the loaded window

Line chart, 253 days from 2025-10-23 to 2026-07-02. Pushes: 31 total, peak 4 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 24 total, peak 7 in a day. Comments: 10 total, peak 3 in a day. Stars: 1,266 total, peak 105 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
pguso543105
LifeHashed7024
hadsie3000
XzenithAI1000
Orvex-tech1001
angad111211000

Recent activity

Latest issues, pull requests and releases

  • Issue comment#4Orvex-tech2026-05-23 07:50
    New Example: Add validation for structured outputs from LLM
  • Issue#21XzenithAI2026-02-20 01:19
    🤖 Resource: Sovereign AI Stack
  • Issue comment#2LifeHashed2025-11-04 04:06
    New Example: Implement comprehensive error handling patterns for agent interactions
  • Issue comment#3LifeHashed2025-11-04 04:06
    New Example: Add retry logic for failed LLM calls and tool executions
  • Pull request#20LifeHashed2025-11-03 13:20
  • Issue comment#17pguso2025-11-03 10:50
    Invalid path of the model after download
  • Issue comment#18pguso2025-11-03 10:30
    Added retry and backoff logic
  • Issue comment#5LifeHashed2025-11-01 06:38
    Enable tool composition and chaining of function results
  • Pull request#18LifeHashed2025-11-01 06:32
  • Issue#17LifeHashed2025-11-01 06:09
    Invalid path of the model after download
  • Issue#16angad111212025-10-30 13:30
    Resource cleanup order mentioned incorrectly in the Code Explanation Readme
  • Issue#14pguso2025-10-29 12:09
    Documentation update for translation.js
  • Issue comment#14pguso2025-10-29 12:09
    Documentation update for translation.js
  • Issue#13pguso2025-10-29 11:45
    Memory issues with simple-agent-with-memory.js
  • Issue comment#13pguso2025-10-29 11:45
    Memory issues with simple-agent-with-memory.js
  • Issue#12pguso2025-10-29 09:18
    Include the logs directory in the repo
  • Issue comment#12pguso2025-10-29 09:18
    Include the logs directory in the repo
  • Issue#13pguso2025-10-28 08:36
    Memory issues with simple-agent-with-memory.js
  • Issue#1pguso2025-10-27 14:42
    Add support for hosted / proprietary AI models via .env configuration
  • Issue#14hadsie2025-10-27 14:32
    Documentation update for translation.js
  • Issue#13hadsie2025-10-27 14:32
    Memory issues with simple-agent-with-memory.js
  • Issue comment#3LifeHashed2025-10-27 08:00
    Add retry logic for failed LLM calls and tool executions
  • Issue#9pguso2025-10-26 18:21
    Update for DOWNLOAD.md
  • Issue#9hadsie2025-10-25 19:43
    Update for DOWNLOAD.md
  • Issue#8pguso2025-10-25 12:08
    Frontend

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,266 stars here means stars gained during the window, not the repo's star count.