Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
ArgosBrain: High-Efficiency AI Coding Agent
Learn how to improve AI coding agent efficiency by amplifying grep and Read with structural facts, reducing redundant file reads and hallucinated symbols.
ArgosBrain — structural engine for AI coding agents.
Opus 4.7 leads the GA SWE-bench Verified leaderboard at 87.6%. We’re aiming for ~95% — by amplifying (not replacing) grep and Read with ArgosBrain. Argos delivers structural facts — every symbol, every caller, every type — in under 50ms at $0 per query. Grep and Read get faster and sharper because they know exactly where to search. We’re publishing the full head-to-head: Opus 4.7 vanilla vs Opus 4.7 + ArgosBrain on SWE-bench Verified.
AI agents like Claude Code and Cursor re-read your codebase every session, burning 73% of their tokens on redundant file reads. ArgosBrain is a local Rust engine that indexes your code into a unified graph (SCIP + LSP + tree-sitter) and serves it to agents via MCP — sub-50ms symbol lookups, $0 per query, zero hallucinated symbols.
Live tested on Kubernetes (~2M LOC), VS Code, and OpenClaw. Per-task cost drops from $0.40 to $0.04 in our benchmarks.
ArgosBrain provides local SCIP-based MCP indexing for code-aware agentic retrieval.
- SCIPSCIP is a language-agnostic indexing protocol that powers precise, cross-repository code navigation for large-scale development environments.Developed by Sourcegraph to replace LSIF, SCIP (Symbolic Code Indexing Protocol) uses Protobuf to serialize code intelligence data like definitions, references, and documentation. It enables sub-second symbol lookups across massive codebases by decoupling the indexing phase from the frontend UI. Tools like scip-typescript and scip-java generate these indexes locally or in CI pipelines, allowing developers to navigate complex dependency graphs without a live Language Server Protocol (LSP) connection. This shift to a serialized format reduces memory overhead and ensures consistent results across different IDEs and web-based code viewers.
- Language Server ProtocolLSP is a JSON-RPC-based protocol that standardizes the communication between a code editor (client) and a language-specific process (server), decoupling language intelligence from the development tool.The Language Server Protocol (LSP) is an open, JSON-RPC-based specification originally developed by Microsoft to solve the M*N complexity problem: supporting M editors for N programming languages. It establishes a common, efficient communication path between a development tool (the client, e.g., VS Code, Vim, Eclipse) and a dedicated language server process. This standardization means a single language server implementation can provide rich 'language smarts'—like code completion, diagnostics, 'go to definition,' and refactoring—to any compliant editor. The protocol, currently at version 3.17, allows language providers to focus on core logic, dramatically accelerating the adoption of advanced coding features across the entire tooling ecosystem.
- tree-sitterAn incremental parsing library that builds concrete syntax trees and updates them efficiently during live editing.Tree-sitter generates robust syntax trees using a C-based runtime and language-specific grammars. It supports over 40 languages (including Rust, JavaScript, and Python) to power features like syntax highlighting and code navigation in Neovim and GitHub. The engine handles syntax errors gracefully and re-parses modified code in O(log n) time. This efficiency ensures immediate feedback without blocking the main editor thread.
- RustRust is a high-performance systems programming language that guarantees memory and thread safety via its compile-time ownership model.Rust is a statically-typed systems language engineered for performance and reliability, directly challenging C/C++ in speed. Its core innovation is the ownership model and 'borrow checker,' which enforces strict memory and thread safety at compile-time, eliminating data races and null pointer dereferences without a conventional garbage collector. Rust achieves near-native speed through 'zero-cost abstractions,' allowing high-level features to compile into highly optimized code. Major industry players, including Microsoft and Cloudflare, leverage Rust for critical infrastructure, and it is now officially supported for development in the Linux kernel.
- MCPMCP is the open-source standard for securely connecting AI agents (like LLMs) to external tools, data, and enterprise workflows.The Model Context Protocol (MCP) functions as a standardized integration layer: think of it as a USB-C port for AI applications. Developed and open-sourced by Anthropic, this protocol allows large language models (LLMs) to access real-time context and execute actions via external tools like GitHub, Jira, or proprietary databases . It uses a simple JSON-RPC interface to define tools, schemas, and endpoints, which enables AI agents to perform complex, state-changing tasks—such as creating a GitHub issue or running a test script—rather than just generating text . MCP is essential for building agentic AI systems that can autonomously pursue goals and operate within defined safety and permission boundaries .