RepoAlerts
SponsorGet alerts

TngSHoO/agentcase-lab

App

Get alerts like thisView on GitHubShare on X

Can I trust it?

Worth a closer look before you use it.

  • Warnings Check

    Very new: it was created 2 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change today.

  • Licence OK

    MIT: 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

Streamlit-based platform for replaying AI agent runs as execution traces and analysing failures. It helps locate root causes such as prompts, retrieval, tool calls, context, memory, permissions or hallucinations, and compares success rate, latency, tokens and cost before and…

Who it's for

AI product and application teams debugging failures in LLM agents

How to use it

Install

python -m pip install -r requirements.txt

From its README. Check it there before running it.

Ready-made installers, when the project publishes them, are on its latest release.

Downloads (if any)

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up TngSHoO/agentcase-lab in my project. Follow its README: https://github.com/TngSHoO/agentcase-lab. Explain each step and check it is safe before running anything.

Star curve

73From 0 to 73 stars between 4 Nov 2026 and 6 Nov 2026.

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.

[![TngSHoO/agentcase-lab on RepoAlerts](https://repoalerts.com/badge/TngSHoO/agentcase-lab.svg)](https://repoalerts.com/repo/TngSHoO/agentcase-lab?ref=badge)
Share on X
  • 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

    LibraryAI agentsGo · 139 stars · +14 this week · 11 days old

  • jwuthri-cloud/Tracely-ai

    Tracely is a self-hostable CI/CD layer for AI agents. It grades production traces with structural checks and LLM judges, clusters failures into issues, freezes failing runs into replayable regression

    AI agentsPython · 1,185 stars · 25 days old

  • Parcha-ai/agentrun

    A TypeScript workflow DSL for defining, validating, inspecting and running repeatable steps, with focused decisions and agent calls. It is part of the AgentRun harness, which also includes pi extensio

    LibraryAI agentsTypeScript · 429 stars · +15 this week · 44 days old

  • joinpactora/relayworks-recovery

    Engine for resuming interrupted AI agent jobs from their last checkpoint instead of restarting them. Completed chunks are sealed and verified, a restricted worker processes only remaining chunks, and

    AppAI agentsTypeScript · 90 stars · +83 this week · 1 day old

  • DAgogo04/gogo-agent

    A small, readable Python codebase for a local-first AI agent harness. It implements a plain loop (observe, reason, act), semantic, episodic and procedural memory stored in a local SQLite file, and a b

    AgentAI agentsPython · 57 stars · 10 days old

  • datawhalechina/agentic-rl-lab

    A collection of reproductions and tutorials of reinforcement learning algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, OPSD, Search-R1, ReTool and ALFWorld. Each method is explained and imp

    ResourceAI agentsPython · 1,224 stars · +699 this week · 123 days old