Skip to main content

Documentation Index

Fetch the complete documentation index at: https://soulforge.proxysoul.com/llms.txt

Use this file to discover all available pages before exploring further.

SoulForge Most AI coding tools treat your codebase as text. They grep, they paste, they match strings. SoulForge treats code as code. It parses every file on launch, builds a live dependency graph, and addresses your work by symbol and line number. Rename a class, move a function, change a return type, the agent uses AST surgery and LSP rename, not find-and-replace.

The first AST editor for AI

Symbol-addressed TypeScript and JavaScript edits via ts-morph. Born from my own 2022 Master’s thesis on programmatic JS to TS conversion. Changing a return type costs a handful of tokens.

Full LSP, your way

Workspace rename, definitions, references, call and type hierarchy, diagnostics, code actions, format. Mason installer for 576+ servers from the TUI.

Compaction with zero LLM

V2 extracts structured state as the conversation happens. When context fills, serialization is instant. Typical sessions compact for free.

Cost tracking, live

Per-model and per-subagent breakdown. Real prices for Claude, OpenAI, Gemini, DeepSeek, Groq, Mistral, Copilot, OpenRouter. Cache-aware. Zero for local models.

Tab-aware file claims

Up to 5 tabs per project, each with its own model, mode, session, and checkpoints. Tabs see each other’s claimed files and active agents. Git hard-blocks during cross-tab dispatch, you never commit partial changes.

Symbol reads, not file dumps

The agent reads a single function by name or jumps via LSP go-to-definition. It navigates the code graph instead of grepping and dumping whole files.

​
Start in 60 seconds

brew tap proxysoul/tap && brew install soulforge
soulforge
Neovim is optional. A Nerd Font is optional. SoulForge prompts to install either on first launch if you want them.

Install

Homebrew, binary, Bun, or source.

Quickstart

Your first five minutes.

FAQ

Do I need Neovim? Which LLM? How much does it cost?

​
Plain-English prompts, real tool calls

> rename AgentBus to CoordinationBus
> move parseConfig from utils.ts to config/parser.ts
> change fetchUser to return Promise<User>
> run tests, fix lint, commit
> research how auth handles refresh tokens
Every line above resolves to a single compound tool call. No multi-step orchestration. No guessing commands.

​
Why it’s different

Live Soul Map

SQLite graph of every file, symbol, and import. Ranked by PageRank and git co-change. Blast-radius tags show how far an edit ripples. Updates as you work.

AST editing for TypeScript and JavaScript

65+ surgical operations via ts-morph. Toggle async, change a parameter, add a method, rename a class member. Atomic batches with rollback.

Full LSP, with Mason installer

Definitions, references, rename, diagnostics, code actions, call and type hierarchy, format, hover. Install servers from Mason’s registry inside the TUI (/lsp install). Works with or without Neovim open.

Symbol reads across 33 languages

Extract one function by name. A 500-line file becomes 20 lines in the prompt. TypeScript, Python, Rust, Go, Java, Kotlin, Scala, Swift, C/C++, Ruby, PHP, Elixir, Zig, Lua, Dart, OCaml, Solidity, Vue, and more.

Cost and speed tracking

Live USD cost broken down by model and by subagent. Cache-aware pricing across Anthropic, OpenAI, Google, DeepSeek, Groq, Mistral, Fireworks, Copilot, OpenRouter, and GitHub Models.

V2 compaction, often free

Structured state extraction as you go — files touched, decisions, failures, tool results. Compaction serializes instantly and usually skips the LLM pass entirely.

Parallel agents with shared cache

Forge dispatches explore, code, and web-search agents in parallel. One agent’s file read is cached for the others. Discoveries propagate across agents within a step.

Task router

Different model per task slot: spark for exploration, ember for code, compact for context, verify for review. Cheap work to cheap models. Mix providers freely.

36 built-in themes

Catppuccin, Dracula, Gruvbox, Tokyo Night, Rose Pine, Kanagawa, Nightfox, Cyberdream, Oxocarbon, and more. Hot-reloaded custom themes from a JSON file.

Sessions and checkpoints

Every turn is a checkpoint with git tags for file rollback. Sessions save as JSONL; resume by short-id prefix. Undo conversation and files in one keystroke.

Local LLMs, zero cost

Ollama and LM Studio auto-detected. Run Llama, Qwen, DeepSeek, Mistral, whatever you have. Cost tracking skips local models automatically.

Skills manager

Browse, install, enable, disable community skills from the TUI (Ctrl+S). Skills resolve from project and global scopes, auto-loaded into the agent prompt.

Remote control [experimental]

Hearth exposes your running forge to Telegram or Discord. Approval prompts arrive as inline buttons. Your code never leaves your host. (Experimental — expect rough edges.)

​
Providers

21 built-in LLM providers. Anthropic, OpenAI, Google, xAI, Groq, DeepSeek, Mistral, Bedrock, Fireworks, MiniMax, Codex, Copilot, GitHub Models, OpenRouter, OpenCode Zen, OpenCode Go, LLM Gateway, Vercel AI Gateway, Proxy, Ollama, LM Studio. Plus any OpenAI-compatible API via custom providers. See all providers.

​
Ready?

Install in one command

brew tap proxysoul/tap && brew install soulforge

Read the FAQ

Common questions, short answers.
Need help? Troubleshooting · GitHub issues · Blog.