Skip to content
View klieret's full-sized avatar
💭
🦊
💭
🦊
683 followers · 168 following

Achievements

Achievement: Starstruckx4Achievement: Pair Extraordinairex3Achievement: Pull Sharkx4Achievement: QuickdrawAchievement: YOLOAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Starstruckx4Achievement: Pair Extraordinairex3Achievement: Pull Sharkx4Achievement: QuickdrawAchievement: YOLOAchievement: Arctic Code Vault Contributor

Highlights

  • Pro

Organizations

@fairinternal @iris-hep @wilson-eft @hsf-training @princeton-nlp @clusterking @b2-hive @dieret @gnn-tracking @cidakima @object-condensation @SWE-bench @SWE-agent @swe-agent-demo @scicode-bench @enigma-agent

Block or report klieret

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
klieret/README.md

📣 NEWS: Check out ProgramBench, a 0% software from scratch benchmark
📣 NEWS: Check out mini-swe-agent, a 100 line AI agent that scores 77% on SWE-bench verified!
📣 NEWS: Check out CodeClash, the first goal-oriented SWE benchmark!

Hi 👋 I'm an AI research scientist at Meta Superintelligence focusing on agentic AI for software development. Some of my smaller open source projects are described here (but it's an incomplete list).

Pinned Loading

  1. SWE-agent/SWE-agent SWE-agent/SWE-agent Public

    SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

    Python 19.2k 2.1k

  2. SWE-agent/mini-swe-agent SWE-agent/mini-swe-agent Public

    The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

    Python 4.3k 588

  3. SWE-agent/SWE-ReX SWE-agent/SWE-ReX Public

    Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.

    Python 494 110

  4. SWE-bench/SWE-smith SWE-bench/SWE-smith Public

    [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents

    Python 644 117

  5. CodeClash-ai/CodeClash CodeClash-ai/CodeClash Public

    Benchmarking Goal-Oriented Software Engineering

    Python 152 16

  6. wandb-offline-sync-hook wandb-offline-sync-hook Public

    A convenient way to trigger synchronizations to wandb / Weights & Biases if your compute nodes don't have internet!

    Python 90 10