Open Source Projects

CSee

A Terminal Monitor for Claude Code, Codex, and Copilot CLI Workflows

CSee is a lightweight terminal dashboard for keeping track of long-running coding-agent sessions. Instead of scrolling through endless output, it parses the agent’s local logs and shows a one-sentence intent for each step of the workflow.

Key Features:

• Live Dashboard: csee watch shows active projects, current status, and full history in real time
• Focused Queries: csee now / csee errors / csee files answer one question at a time
• Zero Intrusion, Zero Cost: Reads only local logs, needs no configuration, makes no LLM calls, and works fully offline

Install with npm install -g csee-monitor.

GitHub npm

HiMe

One-Stop Personal Health AI Agent — "Say Hi to Healthy Me"

HiMe is a self-hosted, privacy-focused AI agent platform for personal health management. It ingests wearable health data in real time and continuously delivers proactive, personalised health insights, with a pixel-art cat digital twin as your companion.

Key Features:

• Real-time Wearable Integration: Ingests 50+ health metrics from Apple Watch and iPhone, including heart rate, HRV, SpO2, sleep stages, and workouts
• Native iOS / watchOS Apps: Direct data syncing and agent control, with in-app streaming chat and push notifications
• Personalised Health Planning: An onboarding survey designs custom recurring check-ins; autonomous analysis is triggered by schedules and events
• Multi-platform Messaging: Chat via Telegram, Feishu, WeChat, or the built-in in-app chat
• Agent-generated Interfaces & Skills: The agent creates personalised pages for repeated workflows, backed by a reusable skills system of analysis playbooks
• Privacy by Design: Fully self-hosted and locally running, so health data never leaves your own machine

Tech Stack:

• Python 3.11+ backend with Docker-ready deployment
• Node.js web dashboard
• Native iOS / watchOS companion apps

GitHub Paper (EMNLP 2026 Demo)

Awesome-Hallu-Eval

A Comprehensive Collection of Hallucination Evaluation Methods

This is a curated list of evaluators designed to assess model hallucination. Here, you can easily find the right tools you need to evaluate and analyze hallucination behavior in language models.

Key Features:

• Comprehensive Coverage: Includes evaluation methods from both before and after the LLM era
• Categorized Methods: Organized by evaluation perspective (Source-Free vs. With-Fact)
• Detailed Documentation: Each method includes data sources, models used, evaluation metrics, and implementation details
• Active Maintenance: Regularly updated with the latest hallucination detection techniques

Research Areas Covered:

• Text Summarization hallucination detection
• Question Answering factuality evaluation
• Dialogue generation consistency assessment
• Multi-modal hallucination detection
• Cross-lingual hallucination evaluation

Impact:

• Potentially used by the NLP research community
• Serves as a go-to resource for hallucination evaluation

GitHub Survey Paper

FHSumBench

Evaluating LLMs' Assessment of Mixed-Context Hallucination Through the Lens of Summarization

This project provides the data and code for our research on evaluating how large language models assess mixed-context hallucination through summarization tasks.

Research Focus:

• Mixed-Context Analysis: Evaluating how LLMs handle conflicting information in source materials
• Self-Assessment Capabilities: Understanding LLMs’ ability to detect their own hallucination patterns
• Summarization Lens: Using summarization as a framework to study hallucination assessment

Key Contributions:

• Novel dataset for mixed-context hallucination evaluation
• Framework for assessing LLM self-evaluation capabilities
• Insights into hallucination detection limitations

Technical Approach:

• Creates scenarios with mixed or conflicting information
• Evaluates LLM performance in detecting inconsistencies
• Analyzes self-assessment accuracy of language models

GitHub Paper (Findings of ACL 2025)