soulforge

作者 proxysoul已验证

Empryo issue tracker + SoulForge (v2) archive — Empryo is the graph-powered AI coding agent that edits symbols, not strings: AST surgery, full LSP, a live code genome. Get it at https://empryo.com

875
Stars
69
Forks
TypeScript
语言
2026/8/23
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/proxysoul/soulforge

快速入门

使用 soulforge 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

Empryo

Empryo

previously SoulForge

The AI coding agent that edits symbols, not strings.

Empryo reads your repository as a living system: it sequences a genome — a live, ranked dependency graph of every symbol — and edits through the AST, never find-and-replace.

Website · Download · Benchmarks · Changelog · Discussions · Discord

Empryo in action

SoulForge is now Empryo — the same symbol-level, graph-powered agent, rebuilt with a desktop app, a faster engine, and a composable core. This repository is Empryo's public home for issues and discussions.

Install

# macOS / Linux
curl -fsSL https://empryo.com/install.sh | bash

# Windows (PowerShell)
irm https://empryo.com/install.ps1 | iex

Official installers and direct downloads are available only from empryo.com/download. Empryo is not distributed through Homebrew, WinGet, or npm.

empryo --set-key anthropic sk-ant-...   # or run locally with Ollama — no key required
cd your-project
empryo

Desktop app and prebuilt binaries: empryo.com/download. Runs on macOS, Linux, and Windows. Do not download Empryo binaries from GitHub Releases or third-party package managers.

Why Empryo

Most coding agents grep, read whole files, and patch strings — they never know what depends on the code they just changed. Empryo builds understanding before it mutates anything:

  • It maps before it reads. On launch, tree-sitter parses your repo into a live graph — every symbol, import, and call site, ranked by PageRank and git co-change. Graph queries answer in milliseconds and cost zero LLM tokens.
  • It knows the blast radius. Before an edit, the agent sees what imports a file, what historically changes with it, and how far a change ripples — "what breaks if I touch this?" is answered before the first keystroke.
  • It edits through the AST. 65+ symbol-level operations, atomic batches with all-or-nothing rollback, structural edits across 30+ languages, and a typecheck as the gate. Nothing breaks on whitespace.
  • It treats tokens as spend. The graph does the navigation models usually burn context on — fewer reads, fewer steps, smaller bills at any scale.

What's inside

Code genomelive dependency graph: tree-sitter across 30+ languages, PageRank + git co-change ranking, blast-radius tags, millisecond search
Symbol-level editing65+ AST operations (atomic, with rollback) + structural edits in 30+ languages
Multi-agentparallel explore/edit agents with a shared I/O cache — cheap models scout, strong models write
Task routerten routable roles, any model in any seat, per tab — your own mixture of experts
Time machineevery prompt is a git checkpoint; rewind code and conversation together, land on any turn
Three surfacesnative desktop app, full terminal UI, headless CLI for scripts and CI — one genome, three phenotypes
LSP + MCP576+ language servers via Mason, any MCP server, 13 lifecycle hooks
Free compactionstructural context compaction with no LLM call — long sessions stay cheap

One agent, many brains

Empryo isn't one model in a loop — it's a crew, and you assign the seats. Every role is a routable slot that takes any model from any of the 22 providers:

brain · spark scout · ember code · explore · verify review · goal review · desloppify · summarize · compact · web search

  • Per tab. Each workspace tab carries its own routing — a frontier model writing code in one tab, a fast cheap one triaging issues in the next, a local model on a private repo in a third.
  • Per config. Set defaults globally or per project; override any slot from the tab. Cheap models scout, strong models write, reviewers judge with clean context.
  • Custom agents. Define your own agents — a prompt, a model, a tool policy — and dispatch them alongside the built-ins. Mix and match providers freely inside a single run.
  • Cache-aware by design. Routing keeps prompt-cache prefixes stable — sub-agents inherit their parent's cache line, so repeated context bills at cache-read rates instead of full price.
  • Costs, itemized. Live spend tracking per model, per sub-agent, per tab, per session, per day — you always know where the tokens went.

Benchmarks

Head-to-head against pi — same models, same repositories, same tasks. The graph does more with less:

Round 1 3 bugs × 3 modelsRound 2 5 real bugs · hono / zod / ky
Bugs fixed8/9 vs 7/97/10 vs 6/10
Cost28% lower — $1.13 vs $1.5823% lower — $7.08 vs $9.19
Wall-clock57% faster — 4m 16s vs 10m32% faster — 22m 30s vs 32m 55s
Efficiency5.7× fewer input tokens — 1.09M vs 6.21M28% fewer steps — 274 vs 382

Round 2 used real bugs from merged PRs (post-training-cutoff, history scrubbed, regression tests injected after each run). Full methodology and transcripts: empryo.com/benchmarks · reproduce at proxysoul/pi-vs-empryo-bench.

Private by design

Empryo runs entirely on your machine. Bring your own key — Anthropic, OpenAI, Google, Groq, DeepSeek, Bedrock, and 16 more, or any OpenAI-compatible endpoint — or run fully local with Ollama / LM Studio. No proxy in the middle, no code leaving your machine, no per-seat fee. Free to use.

SoulForge

SoulForge remains available to download and install, and continues to receive fixes for bugs and critical issues. New features and active development have moved to Empryo.

brew tap proxysoul/tap && brew install soulforge
# or
bun install -g @proxysoul/soulforge

This repository

  • Issues and Discussions — the home for Empryo bug reports, questions, and ideas.
  • The SoulForge source remains archived here under its existing license (see LICENSE).

Sponsors

LLM Gateway

One API, 200+ models, up to 30% off frontier. Wired in as the llmgateway provider.

Sponsor · PayPal · Featured sponsors and all backers

常见问题

What is soulforge?

soulforge is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by proxysoul. Empryo issue tracker + SoulForge (v2) archive — Empryo is the graph-powered AI coding agent that edits symbols, not strings: AST surgery, full LSP, a live code genome. Get it at https://empryo.com. It has 875 GitHub stars.

Is soulforge safe to use?

Yes. soulforge passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install soulforge?

Clone the repository with "git clone https://github.com/proxysoul/soulforge" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is soulforge written in?

soulforge is primarily written in TypeScript. It is open-source under proxysoul on GitHub, so you can review or fork the full source.

Are there alternatives to soulforge?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh soulforge against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI 智能体
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情