Empryo
A graph-aware coding agent that changes code through AST symbols instead of text patches.
- Source repo
- proxysoul/Empryo
- Stars
- ★ 1.6k
- Last updated
- 21d ago
- License
- NOASSERTION
- Primary language
- TypeScript
- FA score
- 50/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformOpenAI API · Claude API
- Cost
- Free software; you pay for model usage
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A developer refactoring a multi-module repository who wants to inspect call sites and likely blast radius before changing a symbol.
- Not a fit if
- Teams wanting to review the current Empryo implementation, since this repo keeps only archived SoulForge source
- Organizations that forbid remote install scripts like curl | bash or irm | iex
- Source review
- 50/100 · Major gaps
What does this agent do, and when should you use it?
Empryo is a locally run AI coding agent formerly known as SoulForge. On launch, it uses tree-sitter to parse a repository into a live graph of symbols, imports, and call sites, ranked with PageRank and Git co-change data. It performs symbol-level AST edits rather than find-and-replace, with atomic batches and rollback. The product is offered through a native desktop app, a full terminal UI, and a headless CLI for scripts and CI, all using the same code genome. This repository serves as Empryo’s public issues and discussions home while retaining archived SoulForge source; active new-feature development has moved to Empryo.
After you run empryo in a project, it parses the repository, indexes symbols, imports, and call sites, and builds a queryable code graph. Before editing, it can surface import relationships, historical co-changes, and blast radius; it then changes code through 65+ symbol-level AST operations and structural edits across 30+ languages. Batches are atomic with rollback, and typechecking is described as the gate for edits. The product also documents parallel explore/edit agents with a shared I/O cache, ten routable roles, MCP server support, language-server support, and Git checkpoints for each prompt.
- A developer refactoring a multi-module repository who wants to inspect call sites and likely blast radius before changing a symbol.
- An engineer working primarily in a terminal who wants to run
empryodirectly inside the target project. - A team adding a headless coding-agent step to a script or CI workflow while using the same code graph as the interactive interfaces.
- A developer with several workspaces who wants one tab routed to a low-cost scouting model and another to a stronger coding model.
- A team handling private repositories locally and choosing either its own provider keys or a local Ollama/LM Studio model setup.
How do you install or deploy this agent?
On macOS/Linux: curl -fsSL https://empryo.com/install.sh | bash. On Windows PowerShell: irm https://empryo.com/install.ps1 | iex. Package-manager options are brew install proxysoul/tap/empryo and winget install ProxySoul.Empryo. Configure Anthropic with empryo --set-key anthropic sk-ant-...; alternatively, run with local Ollama without a key.
How do you use this agent?
Change to the project and start the terminal UI with cd your-project followed by empryo. The documented download page also provides the desktop app and prebuilt binaries. Role routing can be configured globally, per project, or per tab; the README also documents MCP servers and language-server capabilities.
What are this agent's strengths and limitations?
- Navigates through a live graph of symbols, imports, and call sites, with PageRank and Git co-change ranking instead of relying solely on text search.
- Offers 65+ symbol-level AST operations, atomic batching, and rollback for structural changes rather than fragile string replacement.
- Covers native desktop, terminal UI, and headless CLI workflows with one shared code genome.
- Documents routable multi-model roles, 22 providers, local Ollama/LM Studio operation, and OpenAI-compatible endpoints.
- Cloud-model use requires bringing your own provider credentials; local no-key use still requires an Ollama or LM Studio environment.
- The repository says active feature development has moved to Empryo, while this repository is principally for issues, discussions, and archived SoulForge source, so it does not expose the current Empryo implementation for review.
- The documented installation paths include remotely fetched shell or PowerShell scripts, which may conflict with organizational installation or supply-chain policies.
- Advanced language-server functionality depends on language servers managed through Mason, so practical coverage depends on the relevant server and local setup.
How does this agent compare with similar options?
The README reports benchmark comparisons with pi. Across two stated rounds, Empryo reports lower cost and shorter wall-clock time; the second round uses real bugs from hono, zod, and ky. The comparison is limited to the models, repositories, and tasks described there.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Empryo This agent | 50 · Major gaps | CLIFree + model costs | ★ 1.6k | 21d ago | TypeScript | OpenAI API · Claude API |
| Codewhale Terminal Coding Agent | 75 · Some gaps | CLIFree + model costs | ★ 41k | 1d ago | Rust | OpenAI API · Claude API |
| CodeSeek | 48 · Major gaps | CLIFree + model costs | ★ 759 | 3mo ago | Rust | Codex · Claude Code |
| codedb | 60 · Some gaps | MCP serverFree | ★ 1.4k | 10d ago | Zig | ChatGPT · Codex · Claude Code · Claude.ai · OpenAI API · Claude API |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows security mechanisms: SECURITY.md describes forbidden file enforcement, outside-CWD confirmation, shell anti-pattern detection, secret storage, and session permissions. But details on user confirmation (e.g., always asking before edits) are lacking, data flow transparency is limited (no explanation of how tools report data usage), and dependency security is only partially addressed via pinned versions and CI checks. Deductions: insufficient evidence for user confirmation and data flow transparency.
Tests cover AgentBus and AST edit robustness, but CI skips tests, and dependency availability is unverified. Failure messages are evident in tests (e.g., ambiguous errors), but overall reliability evidence is limited. Deductions: CI skips tests, dependency availability unverified.
README describes multiple usage scenarios (desktop, terminal, CLI), capability boundaries are explained (e.g., AST operations), but trigger precision (e.g., command triggers) is not detailed. Environment fit has cross-platform support. Deductions: insufficient evidence for trigger precision.
Information architecture is clear (README, SECURITY, LICENSE), install notes are detailed, but naming stability (SoulForge renamed to Empryo) may cause confusion, examples and FAQ are limited, known limitations are not explicit, versioning changelog is not provided, and maintenance responsibility is unclear. Deductions: insufficient evidence for naming stability, examples, known limitations, versioning, and maintenance responsibility.
Output usability is supported by tests (e.g., extractFinalText), marginal value has benchmark claims, and cost-benefit has claims but unverified. Deductions: benchmarks not independently verified.
Claim traceability is limited (benchmarks link externally), cross-source corroboration is insufficient, and fact-inference separation is unclear. Deductions: lack of independent verification and clear separation.
- Tests are skipped in CI, dependency availability unverified.
- Benchmark claims not independently verified.
- Renaming from SoulForge to Empryo may cause confusion.
- License is BUSL-1.1, not open source, with usage restrictions.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
v2.20.25 SoulForge 2.20.25
Release notes excerpt
[2.20.25] — 2026-07-12 Miscellaneous - publish: bump npm-publish node to 24View on GitHub ↗ -
v2.20.24 SoulForge 2.20.24
Release notes excerpt
[2.20.24] — 2026-07-12 Features - reface repo as Empryo + one-time TUI announcementView on GitHub ↗ -
v2.20.23 SoulForge 2.20.23
Release notes excerpt
[2.20.23] — 2026-07-08 Bug Fixes - intelligence: bound backend parsing and scans to prevent UI freezes (discussion #129)View on GitHub ↗