jushengzhang/CE-Graph
Agent
Can I trust it?
No red flags in our checks.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 13 days ago.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
Reference implementation of a failure-driven loop that refines LLM workflows: it collects failed execution traces, clusters recurring failure modes, proposes prompt or graph edits, and accepts edits only after verification on exemplars. Includes benchmark runners for GSM8K…
Who it's for
Researchers and Python developers evaluating or reproducing LLM workflow refinement with benchmark runners
How to use it
Install
python -m pip install -e .From its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up jushengzhang/CE-Graph in my project. Follow its README: https://github.com/jushengzhang/CE-Graph. Explain each step and check it is safe before running anything.
Star curve
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/jushengzhang/CE-Graph?ref=badge)Similar repos
- jushengzhang/robot-weight-debugging
Research code and experiment logs for an approach where an LLM agent inspects a pretrained robot policy's weights and edits 65 token-embedding rows to repair instruction failures, using simulator feed
- ekzhang/resin
Experimental Python and Rust library of building blocks for LLM inference engines. Provides a headless Rust scheduler, KV cache and metrics server, where the user writes model-specific forward-pass ke
- nuglifeleoji/Sentry
An external runtime failure management layer for LLM agents. It detects invalid actions and behavioral failures such as loops or task drift, guides recovery, verifies that the repair worked, and store
- piercefreeman/waymark
A library for building durable background workflows in Python that survive server restarts, task crashes and long-running jobs. Workflows are plain async code orchestrating distributed actions, with s
- smhanov/agentloop
A Go library that implements the LLM tool-calling loop: it sends prompts to a model, executes requested tool calls, feeds results back, and repeats until a final answer. It adds budgets, hooks, skills
- manuelgscom/inside-llm
A native binary that loads one or two GGUF models via llama.cpp and shows in the browser per-token probabilities, discarded alternatives, sampler effects, and the token where two models' outputs diver