Repository archived — verified 2026-09-30
The
BrokkAi/brokkGitHub repository (GPL-3.0) was archived on 2026-08-21 and is read-only.brokk.ainow redirects to slopcop.com, an AI code-review and static-analysis product from Brokk (founder/CEO Jonathan Ellis, ex-DataStax). The company’s active repos are now static-analysis and agent-protocol tools (Bifrost, Mjolnir ACP terminal client, Anvil ACP server);powerrank(the Brokk Power Ranking benchmark) is archived. No announcement of the IDE’s end-of-life was found, so “discontinued” is inferred from the archive flag and redirect. The notes below describe the 2025 IDE.
Brokk: Under the Hood
1. Introduction
- Brokk is an open source IDE designed for supervising AI coders.
- Focuses on context management for long-form coding in English, not just tab-completion.
- GitHub repository.
2. Quick Context: JLama, MiniLM-L6-v2, and Gemini 2.0 Flash Lite
- Quick Context Suggestions
- Shown as blue suggestions while typing/dictating instructions.
- Can be added to Workspace via right-click.
- Latency Minimization
- Uses Gemini 2.0 Flash Lite for speed.
- GPT 4.1 nano tested but found slower.
- 400ms debounce is standard but not ideal for programmers’ workflow.
- High frequency of calls led to auto-blacklisting by Gemini.
- JLama Integration
- Java-based inference engine (like llama.cpp).
- Uses MiniLM-L6-v2 for semantic embeddings (chosen for speed and size).
- JLama checks if new instructions are semantically distinct before making LLM requests.
3. Deep Scan and Agentic Search: Brute Force and Tool Calls
- Deep Scan
- Suggests additional files needed for a task using brute force (entire summarized project).
- Uses a smarter, slower Edit model LLM; run only on user request.
- Provides more accurate recommendations than Quick Context.
- Recommends whether to edit or summarize files.
- Quick Context vs Deep Scan
- Both are single-turn inference (one-shot recommendations).
- Agentic Search
- Multi-turn process where LLM uses tools to explore codebase.
- Useful when single-turn methods are insufficient (e.g., large projects, missing details).
- Slower but yields high-quality results.
4. Code Intelligence: Joern and Tree-sitter
- Joern as Code Intelligence Engine
- Chosen after evaluating alternatives (CodeQL, SciTools, SonarSource, SCIP, Semgrep, Tree Sitter, LSP).
- Criteria: OSS, no special build integration, type inference, speed on large codebases.
- Downsides: JVM-based (Scala), less uniform API across languages.
- Tree-sitter Integration
- Added in Brokk 0.9 for partial support of non-Java languages (Python, JavaScript, C#).
- Used mainly for summarization to reduce token usage (~10x reduction).
- Utilizes tree-sitter-ng Java wrapper.
5. Conclusion / Wrapping Up
- Brokk empowers users to supervise AI coding while handling editing/syntax details.
- JLama ensures fast suggestions; Joern provides codebase insight; open-source nature allows extensibility.
- Designed for large enterprise codebases, not just demos or small projects.
- Try Brokk.
6. Footer / Additional Links
- Product: Home, Pricing
- Resources: Blog
- Legal: Privacy Policy, Terms of Service
Sources
- https://github.com/brokkai/brokk (accessed 2026-09-30)
- https://github.com/BrokkAi (accessed 2026-09-30)
- https://slopcop.com/ (accessed 2026-09-30; redirect target of brokk.ai)