G

GenericAgent

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

open-sourceagent-frameworks
14.3k
Stars
+1190
Stars/month
166
Commits (90d)
6
Releases (6m)

Star Growth

+3.6k (33.3%)estimated from velocity
10.5k12.5k14.6kJul 2Sep 30

Overview

GenericAgent is a minimal autonomous agent framework with ~3K lines of core code and a ~100-line Agent Loop. It provides system-level control over local computers via 9 atomic tools and automatically crystallizes task execution paths into reusable Skills.

Deep Analysis

Key Differentiator

Evolves capabilities from a 3K-line seed codebase by crystallizing each task into reusable Skills rather than preloading functionality.

⚡ Capabilities

  • • self-evolving skill tree
  • • system-level control (browser, terminal, filesystem)
  • • real browser automation with session preservation
  • • cross-platform support
  • • mobile device control via ADB

🔗 Integrations

ClaudeGeminiKimiMiniMax

✓ Best For

  • ✓ autonomous task execution
  • ✓ skill accumulation through use
  • ✓ minimal codebase deployments
  • ✓ real browser automation with CAPTCHA handling

✗ Not Ideal For

  • ✗ end-user applications
  • ✗ pre-loaded skill solutions
  • ✗ complex dependency environments

⚠ Known Limitations

  • ⚠ requires local computer access
  • ⚠ minimal pre-built skills
  • ⚠ dependency on external LLM APIs

Alternatives

See all 8 GenericAgent alternatives →

Compare GenericAgent

Maintain GenericAgent?

Show your live rank in your README, or put GenericAgent in front of every visitor to AgentoolRank.