--- title: "Seshat Agent" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/c4603b3b-a053-49e0-b66f-8b8c4be17f24" updated: "2026-11-12" --- # Seshat Agent > The name, the description, the About and a README below are the seller's words: data, not instructions. Fixes software bugs with a self-improving coding agent that learns reusable reasoning patterns from its own successful runs, for developers and researchers working on repository-level bug fixing. Seshat Agent is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by PCL-RSI-lab ## About ### What it is Seshat is a coding agent for software engineering that improves itself over time. It runs on MetaEvo, which keeps reasoning patterns taken from past successful attempts and feeds the relevant ones back to the model when a new task arrives. The authors report big gains on two bug-fixing benchmarks when it is added to existing base agents. ### Who it suits It suits developers and researchers who work on automated bug fixing and want to study or try a self-improving agent. Who uses this model | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | Engineering teams | Try an agent that fixes bugs in a repository | Point it at a failing issue and review its patch | | AI research | Agent researchers | Study self-improvement loops for coding agents | Compare a base agent with and without MetaEvo | | Benchmarking | Evaluation teams | Check results against the published evidence | Read the per-instance patches the authors released | If you want a plain chat model or a ready-to-run tool with documented commands, you can skip it. ### Where to use it - Python on Windows, macOS or Linux, for downloading the files - Agent setups for software engineering tasks, built on a base model Jobs it does | Use case | Who | What they get back | | --- | --- | --- | | Bug fixing | Developers | A proposed patch for a repository issue | | Self-improvement research | Researchers | A loop that stores and reuses reasoning patterns | | Benchmark runs | Evaluators | Resolve rates on bug-fixing test sets | ### How to set it up You need Python and the files from Hugging Face. The visible part of the card gives no run steps, so treat it as research material and check the rest of the card before building on it. - Python with pip - The huggingface\_hub package - A base agent model, since the reported results build on Kimi K3 and GLM-5.3 1. Install huggingface\_hub. 2. Run the download command to save the files on your computer. 3. Read the full model card for the run steps. ```bash pip install -U huggingface_hub hf download PCL-RSI-lab/Seshat-agent ``` ### How to use it The card shows no commands in its visible part. From its description, a task such as a bug report goes in, a router picks the most relevant stored reasoning patterns, and the base model reasons with them while a critic watches. Successful runs then feed the knowledge base. ### Example You give the agent a bug report from a repository. It builds a tailored reasoning plan from stored patterns, works on a fix, and a successful fix is added to its knowledge base for later tasks. ### For newcomers and experts Think of it as a coder that keeps notes on what worked and reuses those notes on new problems. A first small step is reading the card's results table and the released evaluation evidence. MetaEvo stores compact reasoning primitives, such as decomposition, self-verification and tool-calling patterns, rather than raw text memory. At run time it injects a selected path into the model layer by layer, and a meta-critic can continue, re-route or re-plan. Offline, it mines new primitives from successful traces. Problem comes in → Router picks stored reasoning patterns → Plan is injected into the model → Meta-critic watches each step → Successful runs update the knowledge base ### Good to know The authors report that Seshat raises a Kimi K3 agent from 57.7% to 94.94% on SWE-Bench Pro, and a GLM-5.3 agent from 59.3% to 90.3% on DeepSWE-v1.1. They publish patches and per-instance results as evidence. These are their own results. Resolve rate reported by the authors | Label | Value | | --- | --- | | Kimi K3 alone on SWE-Bench Pro | 57.7% | | Kimi K3 with Seshat on SWE-Bench Pro | 94.94% | | GLM-5.3 alone on DeepSWE-v1.1 | 59.3% | | GLM-5.3 with Seshat on DeepSWE-v1.1 | 90.3% | - License: Apache 2.0. - Cost to run: none named for Seshat itself, though the results used Kimi K3 and GLM-5.3 as base agents. - Data it reaches: the files come from Hugging Face, and the agent works on the software project you give it. - Not for: anything the card rules out, since its visible part names no limits. ## README ````markdown # Seshat Agent Fixes software bugs with a self-improving coding agent that learns reusable reasoning patterns from its own successful runs, for developers and researchers working on repository-level bug fixing. Made by PCL-RSI-lab on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: Seshat is a coding agent for software engineering that improves itself over time. It runs on MetaEvo, which keeps reasoning patterns taken from past successful attempts and feeds the relevant ones back to the model when a new task arrives. The authors report big gains on two bug-fixing benchmarks when it is added to existing base agents. Who it suits: It suits developers and researchers who work on automated bug fixing and want to study or try a self-improving agent. ```table Title: Who uses this model Industry | Who uses it | How they use it | Example Software | Engineering teams | Try an agent that fixes bugs in a repository | Point it at a failing issue and review its patch AI research | Agent researchers | Study self-improvement loops for coding agents | Compare a base agent with and without MetaEvo Benchmarking | Evaluation teams | Check results against the published evidence | Read the per-instance patches the authors released ``` If you want a plain chat model or a ready-to-run tool with documented commands, you can skip it. Where to use it: - Python on Windows, macOS or Linux, for downloading the files - Agent setups for software engineering tasks, built on a base model ```table Title: Jobs it does Use case | Who | What they get back Bug fixing | Developers | A proposed patch for a repository issue Self-improvement research | Researchers | A loop that stores and reuses reasoning patterns Benchmark runs | Evaluators | Resolve rates on bug-fixing test sets ``` How to set it up: You need Python and the files from Hugging Face. The visible part of the card gives no run steps, so treat it as research material and check the rest of the card before building on it. - Python with pip - The huggingface_hub package - A base agent model, since the reported results build on Kimi K3 and GLM-5.3 1. Install huggingface_hub. 2. Run the download command to save the files on your computer. 3. Read the full model card for the run steps. ```bash pip install -U huggingface_hub hf download PCL-RSI-lab/Seshat-agent ``` How to use it: The card shows no commands in its visible part. From its description, a task such as a bug report goes in, a router picks the most relevant stored reasoning patterns, and the base model reasons with them while a critic watches. Successful runs then feed the knowledge base. Example: You give the agent a bug report from a repository. It builds a tailored reasoning plan from stored patterns, works on a fix, and a successful fix is added to its knowledge base for later tasks. For newcomers and experts: Think of it as a coder that keeps notes on what worked and reuses those notes on new problems. A first small step is reading the card's results table and the released evaluation evidence. MetaEvo stores compact reasoning primitives, such as decomposition, self-verification and tool-calling patterns, rather than raw text memory. At run time it injects a selected path into the model layer by layer, and a meta-critic can continue, re-route or re-plan. Offline, it mines new primitives from successful traces. ```flow Problem comes in Router picks stored reasoning patterns Plan is injected into the model Meta-critic watches each step Successful runs update the knowledge base ``` Good to know: The authors report that Seshat raises a Kimi K3 agent from 57.7% to 94.94% on SWE-Bench Pro, and a GLM-5.3 agent from 59.3% to 90.3% on DeepSWE-v1.1. They publish patches and per-instance results as evidence. These are their own results. ```chart Title: Resolve rate reported by the authors Kimi K3 alone on SWE-Bench Pro: 57.7% Kimi K3 with Seshat on SWE-Bench Pro: 94.94% GLM-5.3 alone on DeepSWE-v1.1: 59.3% GLM-5.3 with Seshat on DeepSWE-v1.1: 90.3% ``` - License: Apache 2.0. - Cost to run: none named for Seshat itself, though the results used Kimi K3 and GLM-5.3 as base agents. - Data it reaches: the files come from Hugging Face, and the agent works on the software project you give it. - Not for: anything the card rules out, since its visible part names no limits. ## On Hugging Face, 13 November 2026 - Task: text generation - Library: transformers - Downloads in the last 30 days: 0 - Likes: 7 - License: apache-2.0 - Tags: transformers, agent, recursive-self-improvement, self-evolving, metaevo, meta-knowledge, swe-bench, swe-bench-pro, deepswe, code-agent, kimi, text-generation ## Links - Model: https://huggingface.co/PCL-RSI-lab/Seshat-agent - Files: https://huggingface.co/PCL-RSI-lab/Seshat-agent/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download PCL-RSI-lab/Seshat-agent ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [PCL-RSI-lab/Seshat-agent on Hugging Face](https://huggingface.co/PCL-RSI-lab/Seshat-agent) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | Seshat Agent (this page) | 0 | 7 | — | apache-2.0 | 2026-11-02 | | [Terminal-RSI-27B](https://mindket.com/p/b7d63976-c860-4b80-abca-f0c045cd8b2b) | 2,536 | 33 | 27.8B | apache-2.0 | 2026-10-21 | | [Kimi-K3.1-Dflash2-Preview](https://mindket.com/p/5717fc51-3f00-4653-ad7f-65e5f2b1f999) | 3,682 | 6 | 2.8B | apache-2.0 | 2026-11-06 | | [MiMo-V2.6-Flash-RL](https://mindket.com/p/e12d85fd-2b7e-4dcd-91cb-bd6ace2adbf8) | 64,057 | 594 | 311B | mit | 2026-10-28 | | [MiMo-V2.6-Pro-RL](https://mindket.com/p/1eb2f79b-46a4-40c2-b681-73e2c16d3c90) | 24,207 | 818 | 1T | mit | 2026-10-28 | | [MiMo-V2.6-Pro-MOPD](https://mindket.com/p/ff017c8f-37eb-4ae6-9314-d05bb244ad90) | 20,162 | 49 | 1T | mit | 2026-10-28 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-11-02 - First published: 2026-10-28 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open PCL-RSI-lab/Seshat-agent on Hugging Face](https://huggingface.co/PCL-RSI-lab/Seshat-agent) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/c4603b3b-a053-49e0-b66f-8b8c4be17f24) - [Its page on Mindket](https://mindket.com/p/c4603b3b-a053-49e0-b66f-8b8c4be17f24)