SuperCoder Desktop
A local desktop coding agent for planning, editing, and reviewing work in your own codebase.
- Source repo
- TransformerOptimus/SuperCoder
- Stars
- ★ 1k
- Last updated
- 4mo ago
- License
- MIT
- Primary language
- Rust
- FA score
- 53/100 · 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
- Medium · a few setup steps
- You'll need
- Typical use
- A developer who wants to edit a local project in place, inspect diffs, and return to earlier checkpoints.
- Not a fit if
- Teams that need a ready-made installer; only source builds exist today
- Teams that need fully offline operation with no cloud model calls
- Users unwilling to install Rust, Node, and Docker build tooling
- Source review
- 53/100 · Major gaps
What does this agent do, and when should you use it?
SuperCoder is a local-first, open-source desktop coding agent that uses credentials supplied by the developer. Its Tauri 2 and React desktop application is a thin adapter over a pure-Rust agent core with Ask, Plan, and Coding modes, subagents, skills, tool approval, and prompt caching. The app supports in-place edits, checkpoints and rewind, diff review, an interactive terminal, and a file explorer for a selected local folder. An optional Go Context Engine indexes repositories with tree-sitter, vector retrieval, a call graph, and BM25, backed by Qdrant and FalkorDB. The current product is built from source; the legacy 2024 pipeline in v1/ is frozen and is neither maintained nor built.
After the user configures a provider's base_url, api_key, and model in Settings, they create a session, choose a folder, and select Ask, Plan, or Coding mode. The desktop app delegates to the Rust agent core, whose documented harness includes a loop, tools, modes, subagents, skills, tool approval, and prompt caching; the app can make in-place edits, show diff review, provide checkpoints and rewind, and expose an interactive terminal and file explorer. When Settings → Context engine is enabled, a locally run docker compose service indexes the repository through tree-sitter into vector, call-graph, and BM25 retrieval structures. The agent queries that service through codebase_search and codebase_graph. Model requests go directly from the machine to the configured OpenAI chat-completions or Anthropic Messages API.
- A developer who wants to edit a local project in place, inspect diffs, and return to earlier checkpoints.
- An engineer who wants to outline a change in Plan mode before carrying it out in Coding mode.
- A contributor working in a large repository who needs call-graph, vector, and lexical retrieval to find relevant code.
- A developer with OpenAI chat-completions or Anthropic Messages credentials who wants to configure their own provider endpoint and model.
- A desktop-focused programmer who wants file browsing and an interactive terminal alongside an agent session.
How do you install or deploy this agent?
Install Rust stable, the Tauri 2 system prerequisites for your OS, Node.js 20+, and npm. Then run:
cd apps/desktop
npm install
npm run tauri:devTo build a release bundle, run npm run tauri:build. On first launch, add an LLM provider in Settings with base_url, api_key, and model. The optional Context Engine also requires Docker with Compose:
cd services/context-engine
cp .env.example .env
docker compose up -d --buildSet SUPERCODER_OPENAI_API_KEY in .env, then enable Settings → Context engine in the app.
How do you use this agent?
Launch the desktop app and configure an LLM provider in Settings. Create a session, select the folder to work in, and choose Ask, Plan, or Coding mode. For repository-scale structural retrieval, start the Context Engine and enable Settings → Context engine; the agent can then use codebase_search and codebase_graph. Use checkpoints and rewind during changes, and inspect results with diff review.
What are this agent's strengths and limitations?
- Requests go directly from the developer's machine to the configured model provider, without an intermediary vendor backend.
- The pure-Rust agent core is separated from the Tauri 2 and React desktop adapter.
- Its optional Context Engine combines tree-sitter, vector search, call-graph retrieval, and BM25 for repository navigation.
- The local workflow includes in-place editing, diff review, checkpoints and rewind, a terminal, and a file explorer.
- Prebuilt binaries are not yet available, so adoption currently requires building from source.
- Users must supply a provider base_url, api_key, and model; model requests still go to the provider they choose.
- The optional Context Engine adds Docker Compose deployment and requires SUPERCODER_OPENAI_API_KEY.
- The legacy v1/ pipeline is frozen, unmaintained, and not built.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| SuperCoder Desktop This agent | 53 · Major gaps | Desktop appFree + model costs | ★ 1k | 4mo ago | Rust | OpenAI API · Claude API |
| OpenTeams | 55 · Major gaps | Desktop appFree + model costs | ★ 582 | 26d ago | TypeScript | Codex · Claude Code |
| Waku Coding Agent Desktop | 50 · Major gaps | Desktop appFree + model costs | ★ 1.6k | 1mo ago | Rust | Codex · Claude Code |
| Caprock | 83 · Good | Desktop appFreemium | ★ 41 | 1d ago | Go | Codex · Claude Code · OpenAI API · Claude API |
How does FollowAgents rate this agent?
Why each dimension lost points
The README says code stays local and goes directly to the model provider selected by the user; bench-runner reads the API key only from the environment, and SECURITY.md describes some key exposure boundaries. This supports scores of 2 for data-flow transparency and sensitive-data handling. The README mentions tool approval, checkpoints, and rewind, but the supplied code does not establish permission granularity, confirmation for each kind of external action, or complete recovery guarantees, so least privilege, user confirmation, external effects, and rollback are not full marks. The dependency list is concrete, but the packet provides no vulnerability status or mitigation evidence; publisher identity is unknown and author verification is not clear, so dependency security and source attribution each score 1.
The README, Cargo workspace, Rust entry points, and CI broadly describe a consistent desktop agent with an optional Context Engine; CI lists compilation, test, and service-build jobs, supporting a score of 2 for self-consistency. Dependency availability is supported only by version listings, with no supply-chain or availability evidence, so it scores 1. bench-runner emits errors and has nonzero exit paths for task-spec read failures and execution failures, scoring 2 for failure messages; the packet does not show the full application's error experience, so this is not full marks.
The README identifies desktop developers, Ask / Plan / Coding modes, BYO keys, and optional structured retrieval, and distinguishes the frozen v1 tree from the current product; audience and boundaries score 2. Example commands and setup steps identify Rust, Tauri, Node, and Docker requirements, so environment fit scores 2. The packet does not clearly define when to choose the agent or a mode, or how triggers are constrained, so trigger precision scores 1.
The README provides repository layout, an architecture link, getting-started steps, and optional-service instructions, supporting scores of 2 for information architecture and install notes; naming is broadly consistent in the supplied files and scores 2. Commands are provided but there is no FAQ, so examples and FAQ score 1. The README states that prebuilt releases are not yet available, the Context Engine is optional, and v1 is frozen and unmaintained, supporting a score of 2 for known limitations. The LICENSE contains the full MIT license text and scores 3. The packet has no changelog or clearly identified maintainer; the roadmap and private vulnerability reporting path are not enough to establish version history or ongoing maintenance ownership, so those criteria each score 1.
bench-runner emits structured JSON with patch, summary, tool-call, and token fields; the README also describes diff review, checkpoints, and search features, supporting a score of 2 for output usability. Graph, vector, and lexical retrieval plus multiple agent modes offer identifiable added value, but retrieval benefits remain product claims and benchmarking is listed as future work, so marginal value scores 2. Setup requires building from source and configuring a key; the optional service adds Docker and an embedding key. With no cost or performance evidence, cost-benefit scores 1.
README claims can be compared with the architecture overview, CLI fields, dependency manifest, and CI jobs, supporting scores of 2 for claim traceability and cross-source corroboration. The README separates current features, optional features, and roadmap items, while bench-runner comments distinguish CLI inputs from task-spec inputs, supporting a score of 2 for fact-inference separation. These scores reflect only the supplied static material and do not imply execution verification.
- This assessment uses only the supplied static excerpts; unseen files remain unknown, and no execution or independent testing was performed.
- Before use, confirm the agent tools' actual approval and rollback behavior, and which code and prompt content the model provider receives.
- Prebuilt installers are not yet available; enabling the Context Engine requires Docker and a server-side embedding key.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/supercoder)<a href="https://followagents.com/en/agents/supercoder"><img src="https://followagents.com/badge/supercoder.svg" alt="FARS review"></a>Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
Changes - Bench-runner v0.1.7: expose LLM + tool policy knobs as CLI / env tunables @adithyn7 (#136)View on GitHub ↗ -
Release notes excerpt
Changes - Bench-runner LLM transport fix: HTTP/1.1 + no pool + 15s header timeout (LlmPolicy) @adithyn7 (#135)View on GitHub ↗ -
Release notes excerpt
Changes - Bench-runner tool fixes: timeouts, ignore-list, result caps (ToolPolicy) @adithyn7 (#134)View on GitHub ↗
FAQ
Is SuperCoder tied to one model provider?
Does code pass through a SuperCoder backend?
Is the Context Engine required?
What runtime prerequisites are required?
Thanks — we use this to improve the page.