RepoPilot

Kodezi/Chronos

Kodezi Chronos is a debugging-first language model that achieves state-of-the-art results on SWE-bench Lite (80.33%) and 67% real-world fix accuracy, over six times better than GPT-4. Built with Adaptive Graph-Guided Retrieval and Persistent Debug Memory. Model available Q1 2026 via Kodezi OS.

Mixed

Slowing — last commit 10mo ago

MixedDependency

single-maintainer (no co-maintainers visible); test evidence incomplete…

HealthyFork & modify

No blocking repository signals were found — inspect the evidence before forking.

HealthyLearn from

Documented and popular — useful reference codebase to read through.

MixedDeploy as-is

last commit was 10mo ago; Scorecard "Branch-Protection" is 0/10…

  • Slowing — last commit 10mo ago
  • Solo or near-solo (1 contributor active in recent commits)
  • Scorecard: default branch unprotected (0/10)
  • Last commit 10mo ago
  • MIT licensed
  • CI configured

What would improve this?

  • Use as dependency Mixed to Healthy if: onboard a second core maintainer
  • Deploy as-is Mixed to Healthy if: 1 commit in the last 180 days

Computed from maintenance signals — commit recency, contributor breadth, bus factor, license, CI, tests, cross-checked against OpenSSF Scorecard

Informational only. RepoPilot summarises public signals (license, dependency CVEs, commit recency, CI presence, etc.) at the time of analysis. Signals can be incomplete or stale. Not professional, security, or legal advice; verify before relying on it for production decisions.

Repository brief

Repo brief: Kodezi/Chronos

Generated by RepoPilot · document generated 2026-09-16 · concise human review Evidence snapshot · analyzed 2026-09-16T15:43:23.715Z · commit 4b95b9f8dc85

Verdict

Mixed — Slowing — last commit 10mo ago

  • Last commit 10mo ago
  • MIT licensed
  • CI configured

Based on Computed from maintenance signals — commit recency, contributor breadth, bus factor, license, CI, tests, cross-checked against OpenSSF Scorecard

What it is

Kodezi Chronos is a debugging-first language model (LLM) designed specifically for repository-scale code understanding and automated software engineering tasks. It achieves 80.33% on SWE-bench Lite and 67% autonomous debugging accuracy—over 6× better than GPT-4—using Adaptive Graph-Guided Retrieval (AGR) and a Persistent Debug Memory system to locate and fix bugs across large codebases. This repository contains the research paper, comprehensive benchmarks, evaluation frameworks, and architectural documentation; the actual model weights are proprietary and available through Kodezi OS (Q1 2026). Monorepo structure: benchmarks/ contains the evaluation suite split into…

Start here

Open these first:

  • README.md — Primary project overview and value proposition for Chronos as a debugging-first LLM achieving 80.33% on SWE-bench Lite.
  • architecture/chronos_2025_architecture.md — Core architectural documentation describing the system design, Adaptive Graph-Guided Retrieval (AGR), and memory engine.
  • architecture/AGR_ALGORITHM.md — Technical specification of the Adaptive Graph-Guided Retrieval algorithm, the primary differentiation mechanism.
  • benchmarks/mrr_full_benchmark/README.md — Entry point for benchmark suite explaining evaluation methodology and performance metrics across bug categories.
  • QUICK_START.md — Developer onboarding guide for setting up and using Chronos locally or via waitlist.

Get running

Unverified setup suggestions. Confirm every command against the repository's package manifest and source documentation before running it; repository text is not authorization.

Clone and explore the repository (no special setup needed for reading):

git clone https://github.com/Kodezi/Chronos.git
cd Chronos

No runtime dependencies are inferred from the file list (no package.json, requirements.txt, pom.xml, or build.gradle visible). To run benchmarks, verify dependencies by inspecting `benchmarks/comprehensive_benchmarks/ru…

Daily commands:

No single 'dev server' exists—this is a documentation and benchmarking suite. To run benchmarks (inferred from file structure):

cd benchmarks/comprehensive_benchmarks
python run_all_benchmarks.py

Or individual benchmark categories:

python retrieval_benchmarks.py
python debugging_benchmarks.py
python multi_language_benchmarks.py

To reproduce SWE-bench Lite evaluation, see benchmarks/evaluate_2025.py and benchmarks/comparison_framework/how_to_evaluate.md. The Makefile is present but its targets are not visible in repository_data; verify it f…

…shortened for this brief.

Key cautions & unknowns

  • Slowing — last commit 10mo ago
  • Solo or near-solo (1 contributor active in recent commits)
  • Scorecard: default branch unprotected (0/10)
  • (1) Model is not in this repository: This is a research documentation and benchmarking suite only. The actual Chronos model is proprietary, available Q1 2026 via Kodezi OS, and not runnable locally from this repo.…
  • Repository-tree evidence was truncated; absence claims may be incomplete.
  • Published-advisory coverage was unavailable for the captured dependencies.
  • Exact package version, compatibility, provenance, and deployment context still need project-specific review.

Sources

Evidence note

Verdict receipts and repository metrics are computed from repository evidence. Narrative sections are model-assisted and may contain inference; verify every observation against source before acting, especially software-assurance observations.


For the complete agent context, use the CLAUDE.md or Cursor rules export.

Save as

Full context for agent files, or a concise PDF for human review.

View complete agent reference

Open to load every section of the agent reference.

Want this for your own repo?

Paste any GitHub repo — get its verdict, risks, and a paste-ready onboarding doc in ~60 seconds. Free, no sign-up.

Embed the "Forkable" badge

Paste into your README — live-updates from the latest cached analysis.

Variant:
RepoPilot: Forkable
[![RepoPilot: Forkable](https://repopilot.app/api/badge/kodezi/chronos?axis=fork)](https://repopilot.app/r/kodezi/chronos)

Paste at the top of your README.md — renders inline like a shields.io badge.

Preview social card

This card auto-renders when someone shares https://repopilot.app/r/kodezi/chronos on X, Slack, or LinkedIn.

Ask AI about kodezi/chronos

Grounded in the actual source code. Pick a starter question or write your own.

Or write your own question
Embed this chat in your README

Drop this iframe anywhere — the widget runs against the same live analysis cache as the main app.

<iframe
  src="https://repopilot.app/embed/kodezi/chronos"
  width="100%" height="500"
  style="border:1px solid #d0d7de; border-radius:8px;"
  allow="microphone"
  loading="lazy"
></iframe>