CommitDistill: A Lightweight Knowledge-Centric Memory Layer for Software Repositories

• URL: http://arxiv.org/abs/2605.18284v1
• Date: Mon, 18 May 2026 12:14:28 GMT
• Title: CommitDistill: A Lightweight Knowledge-Centric Memory Layer for Software Repositories
• Abstract summary: Software accumulate large amounts of unstructured knowledge in commit messages, pull-request discussions, and issue threads.<n>Recent work on typed-memory architectures for agents (MemGPT, generative agents, and the PlugMem module of Yang et al.) argues that agent memory should be distilled, typed knowledge rather than raw interaction text.<n>We adapt that stance to a software repository's own git history under a constrained regime: deterministic, dependency-free, local-only, no embeddings.
• Score: 0.5872014229110213
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Software repositories accumulate large amounts of unstructured knowledge in commit messages, pull-request discussions, and issue threads, but developers and AI coding assistants rarely reuse this history effectively. Recent work on typed-memory architectures for LLM agents (MemGPT, generative agents, and the PlugMem module of Yang et al.) argues that agent memory should be distilled, typed knowledge rather than raw interaction text. We adapt that stance to a software repository's own git history under a constrained regime: deterministic, dependency-free, local-only, no embeddings. We present CommitDistill, an open-source Python prototype that mines a local git history into typed knowledge units (Facts, Skills, Patterns) using deterministic regex and surfaces them through a TF-IDF retriever with a calibrated silence threshold (theta = 2.5) that abstains on out-of-distribution queries. The artefact is a trust-instrumented memory substrate: deterministic, no external service, inspectable plain-JSON store, tunable abstention. A case study on five public repositories spanning Python, JavaScript, C, and Java (25,000 commits, 1,167 extracted units) reports useful-precision 0.525 at Cohen's kappa = 0.633 on 40 dual-annotated Python units. The decisive finding is budget-constrained retrieval: at a 256-character per-query budget, CommitDistill reaches 0.750 hit-rate on a 12-query benchmark against BM25's 0.333 and git log --grep's 0.083. On a four-arm paired LLM-as-judge evaluation (n=200 time-travel bug-fixes, two judges) covering control, CommitDistill, a body-budget-matched CD-Hybrid, and BM25, no condition produces a statistically detectable lift over control on the headline mean and CD-Hybrid is indistinguishable from BM25 head-to-head. Extraction over 10,000 commits completes in under 4 seconds on a laptop. Source, annotations, baselines, and a reproducibility script accompany this paper.

Related papers

• Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills [86.15447717549154]
  We present DisCo, a skill-powered research agent that creates skills and uses them during research.<n>We call this missing layer operational knowledge, the know-how that separates knowing a method from making it work.
  arXiv  Detail & Related papers  (2026-09-02T15:49:41Z)
• Stylometric Defenses Against Author Impersonation in Software Repositories [0.0]
  Cross-modal patch-level embeddings can support behavioral triage against author impersonation in real-world repositories.<n>We fine-tune a cross-modal transformer on more than 20 years of Linux kernel commit history to embed code diffs and commit messages into a unified stylometric space.
  arXiv  Detail & Related papers  (2026-08-03T11:02:13Z)
• MediaWiki Code2Code Search: Neural Retrieval for the Semantic Discovery of Open-Source Software Entities [0.5279475826661643]
  We present Code2 InformationCode Search, a neural retrieval system for semantic code-to-code discovery.<n>By 1.29 million structural (functions, types, and templates) Code across 2,500+ large repositories, our system enables retrieval based on computational intent.<n>We employ a split-build architecture, decouplingintensive offline indexing from a CPU-only serving layer.
  arXiv  Detail & Related papers  (2026-07-29T11:07:07Z)
• Why Git Is the Memory Solution for the Agentic Development Lifecycle [0.0]
  We argue memory should be git-bound, built into the repository's version control.<n>On this ledger we solve two problems separately, then combine them.<n>A router dispatches breadth to a git-anchored structural map, pointed lookups to confidence-gated episodes, and rationale to decision synthesis.
  arXiv  Detail & Related papers  (2026-07-15T22:06:59Z)
• FluctlightDB: A Memory Model of Data for AI Agents [1.3537117504260623]
  FluctlightDB is an embedded engine that implements this contract via experience() and activate.<n>On LoCoMo, CHORUS recalls 99.0% on an internally reproduced July 2026 run.
  arXiv  Detail & Related papers  (2026-07-10T09:18:32Z)
• Entity-Collision: A Stratified Protocol for Attributing Retrieval Lift in Agent Memory [0.0]
  End-to-end agent-memory benchmarks report a single hit@k per retriever.<n>We propose entity-collision, a system-agnostic protocol that pins the BM25 floor by construction.
  arXiv  Detail & Related papers  (2026-05-28T09:02:48Z)
• Nautilus Compass: Black-box Persona Drift Detection for Production LLM Agents [2.417342411475111]
  Nautilus Compass is a black-box drift detector and agent memory layer for production coding agents.<n>The system ships as a Claude Code plugin, an MCP 20245 A2A server, a CLI, and an API on one daemon.
  arXiv  Detail & Related papers  (2026-05-11T01:49:17Z)
• FGDM: Reasoning Aware Multi-Agentic Framework for Software Bug Detection using Chain of Thought and Tree of Thought Prompting [0.0]
  The Flow-Graph-Driven Multi-Agent Framework (FGDM) is composed of four agents that operate in a sequential manner.<n>The framework converts the received code to a flow graph, identifies the erroneous segments, and further generates the repaired code.
  arXiv  Detail & Related papers  (2026-04-27T17:22:15Z)
• Selective Memory for Artificial Intelligence: Write-Time Gating with Hierarchical Archiving [0.0]
  Parametric approaches compress knowledge into weights, precluding selective updates.<n>We introduce write-time gating that filters incoming knowledge objects using composite salience scores.
  arXiv  Detail & Related papers  (2026-03-16T23:06:44Z)
• SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution [56.9361004704428]
  Large Language Models (LLMs) have demonstrated remarkable proficiency across a variety of complex tasks.<n>SWE-Fixer is a novel open-source framework designed to effectively and efficiently resolve GitHub issues.<n>We assess our approach on the SWE-Bench Lite and Verified benchmarks, achieving competitive performance among open-source models.
  arXiv  Detail & Related papers  (2025-01-09T07:54:24Z)
• PyPulse: A Python Library for Biosignal Imputation [58.35269251730328]
  We introduce PyPulse, a Python package for imputation of biosignals in both clinical and wearable sensor settings.<n>PyPulse's framework provides a modular and extendable framework with high ease-of-use for a broad userbase, including non-machine-learning bioresearchers.<n>We released PyPulse under the MIT License on Github and PyPI.
  arXiv  Detail & Related papers  (2024-12-09T11:00:55Z)
• Zero-Shot Detection of Machine-Generated Codes [83.0342513054389]
  This work proposes a training-free approach for the detection of LLMs-generated codes. We find that existing training-based or zero-shot text detectors are ineffective in detecting code. Our method exhibits robustness against revision attacks and generalizes well to Java codes.
  arXiv  Detail & Related papers  (2023-10-08T10:08:21Z)
• VulLibGen: Generating Names of Vulnerability-Affected Packages via a Large Language Model [13.96251273677855]
  VulLibGen is a method to directly generate affected packages. It has an average accuracy of 0.806 for identifying vulnerable packages. We have submitted 60 vulnerability, affected package> pairs to GitHub Advisory.
  arXiv  Detail & Related papers  (2023-08-09T02:02:46Z)
• Precise Zero-Shot Dense Retrieval without Relevance Labels [60.457378374671656]
  Hypothetical Document Embeddings(HyDE) is a zero-shot dense retrieval system. We show that HyDE significantly outperforms the state-of-the-art unsupervised dense retriever Contriever.
  arXiv  Detail & Related papers  (2022-12-20T18:09:52Z)
• A ground-truth dataset and classification model for detecting bots in GitHub issue and PR comments [70.1864008701113]
  Bots are used in Github repositories to automate repetitive activities that are part of the distributed software development process. This paper proposes a ground-truth dataset, based on a manual analysis with high interrater agreement, of pull request and issue comments in 5,000 distinct Github accounts. We propose an automated classification model to detect bots, taking as main features the number of empty and non-empty comments of each account, the number of comment patterns, and the inequality between comments within comment patterns.
  arXiv  Detail & Related papers  (2020-10-07T09:30:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.