EvoForge
smallchao/EvoForge
EvoForge is a local-first AI agent workbench that continuously learns and retains memory across tasks rather than starting from zero each day.
99 0No licenseUpdated 2026-08-12
68
GoodOverview
EvoForge is built as a complete desktop application in Rust and Tauri that provides a continuous task loop: plan, execute, verify, deliver, and distill. Unlike standard chat interfaces, it automatically turns successful execution patterns into reusable skills, saves project context into editable memory, and includes built-in tools for terminal, file manipulation, git operations, and embedded browser navigation.
Capabilities
- ▸Autonomous goal planning and execution
- ▸Skill distillation and persistent local memory
- ▸Embedded browser scraping and interaction
- ▸Terminal execution with clean output handling
- ▸File and Git management including patches and pull requests
- ▸MCP server integration with automatic OAuth PKCE authentication
Best for
Executing autonomous, long-running coding and development goals with a token budget, Distilling repeated terminal and file operations into persistent, reusable skills, Integrating local workspaces with GitHub, Cloudflare, Supabase, and custom MCP servers, Searching through full-text logs of past sessions and auditing accumulated agent experience
Works with
CursorCodex
Evoa Score breakdown= Σ (score × weight)
68Task usefulness20%100 → +20.0
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%100 → +15.0
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%34 → +4.1
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%80 → +12.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%50 → +4.0
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%50 → +2.5
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total79.6 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
EvoForge operates on a local-first architecture storing data in ~/.evoforge, featuring configurable sandbox levels, confirmation prompts for destructive operations, and an audit trail.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.