Browse code by meaning

Enhancing repository-level code completion with selective retrieval

Self-supervised method for learning when to retrieve contextual information from a code repository speeds up code completion times by 70% while increasing accuracy.

Github Code Search - Programmers' Goldmine

Learning new language or framework can sometimes be a struggle. Traditional approach is to read documentation which explains the concepts, and provides simple examples. Sometimes that might be enough, but what those documentations are often lacking are some advanced examples and usages in real projects.

Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches

Recent advancements in large language models (LLMs) have substantially improved automated code generation. While function-level and file-level generation have achieved promising results, real-world software development typically requires reasoning across entire repositories. This gives rise to the challenging task of Repository-Level Code Generation (RLCG), where models must capture long-range dependencies, ensure global semantic consistency, and generate coherent code spanning multiple files or modules. To address these challenges, Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm that integrates external retrieval mechanisms with LLMs, enhancing context-awareness and scalability. In this survey, we provide a comprehensive review of research on Retrieval-Augmented Code Generation (RACG), with an emphasis on repository-level approaches. We categorize existing work along several dimensions, including generation strategies, retrieval modalities, model architectures, training paradigms, and evaluation protocols. Furthermore, we summarize widely used datasets and benchmarks, analyze current limitations, and outline key challenges and opportunities for future research. Our goal is to establish a unified analytical framework for understanding this rapidly evolving field and to inspire continued progress in AI-powered software engineering.

Top2Vec: Distributed Representations of Topics

Topic modeling is used for discovering latent semantic structure, usually referred to as topics, in a large collection of documents. The most widely used methods are Latent Dirichlet Allocation and Probabilistic Latent…

Building an Open-Source Alternative to Cursor with Code Context - Milvus Blog

Code Context—an open-source, MCP-compatible plugin that brings powerful semantic code search to any AI coding agent, Claude Code and Gemini CLI, IDEs like VSCode, and even environments like Chrome.

Paper page - Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature

Join the discussion on this paper page

ARCHITECTURE.md

SYSTEM TEMPLATE FOR RAPID CODEBASE COMPREHENSION - HAVE YOUR AGENT TO FILL IN FOR YOUR REPO

Sourcegraph — Code Understanding, Oversight and Evolution

Give humans and agents complete context to understand, oversee, and evolve the world's largest, most complex codebases.

Elicitation - Model Context Protocol

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

ooh.directory: a place to find good blogs that interest you

A collection of 2,385 blogs about every topic

RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation

The task of repository-level code completion is to continue writing the unfinished code based on a broader context of the repository. While for automated code completion tools, it is difficult to utilize the useful information scattered in different files. We propose RepoCoder, a simple, generic, and effective framework to address the challenge. It streamlines the repository-level code completion process by incorporating a similarity-based retriever and a pre-trained code language model in an iterative retrieval-generation pipeline. RepoCoder makes effective utilization of repository-level information for code completion and has the ability to generate code at various levels of granularity. Moreover, we propose a new benchmark RepoBench, which consists of the latest and high-quality real-world repositories covering line, API invocation, and function body completion scenarios. Experimental results indicate that RepoCoder significantly improves the In-File completion baseline by over 10% in all settings and consistently outperforms the vanilla retrieval-augmented code completion approach. Furthermore, we validate the effectiveness of RepoCoder through comprehensive analysis, providing valuable insights for future research. Our source code and benchmark will be publicly available after the paper review.

SemRepo: A Knowledge Graph for Research Software and Its Scholarly Ecosystem

We present SemRepo, an RDF knowledge graph comprising over 81 million triples describing nearly 200,000 GitHub repositories associated with scientific research. SemRepo captures repository-level metadata, such as contributors, issues, and programming languages, and interlinks this information with external scholarly knowledge graphs. In particular, repository authors are linked to their profiles in SemOpenAlex, repositories are connected to scholarly publications in LPWC, and research artifacts, such as datasets and experiments, are linked via MLSea-KG. This integration enables queries that span publications and their scholarly artifacts, which are typically fragmented across separate platforms. SemRepo supports analyses that are difficult to perform with existing resources in isolation, including provenance reconstruction across repositories and publications, as well as the systematic identification of risks to research reproducibility and software sustainability. By unifying research software with its scholarly context in a single graph, SemRepo provides an important infrastructure for large-scale analysis of software within the broader scientific research ecosystem.

Git in six hundred words

(This essay is a companion piece to Gitlet, my implementation of Git in JavaScript.)

atproto-aware concept search engine

a mockup of a webpage search engine that only indexes webpages that are referenced in atproto records. Surfaces related links based on social and community context.

/code

/code in Google Labs contains various experiments for code and software development