3 repository-uri
Capabilities for clearing the current conversation and starting a fresh session without restarting the process.
Distinct from Session Data Clearing: Distinct from Session Data Clearing: focuses on resetting conversational AI sessions rather than clearing browser history and cookies.
Explore 3 awesome GitHub repositories matching web development · Conversation Resets. Refine with filters or upvote what's useful.
TaskWeaver is an LLM agent framework that interprets natural language requests and executes them as Python code, SQL queries, or shell commands. It functions as a conversational code interpreter that maintains stateful data structures across turns, generating executable code from user prompts within a session-based environment. The system is designed as a self-hosted AI agent platform that can be deployed in Docker, managing sessions and providing a web UI for data analytics and automation tasks. The framework distinguishes itself through a role-based multi-agent architecture that divides the
Clears the current conversation and starts a fresh session without restarting the process.
ChatGPT-wechat-bot is a chatbot automation system that integrates a large language model into WeChat to automatically generate and send replies in both private and group conversations. The project employs an event-driven pipeline that uses keyword-based trigger filtering and mention patterns to control when the bot responds. It manages multi-turn dialogues through stateful context management, which stores conversation history in memory and allows for session-based history clearing via designated commands. The system connects to remote models via API requests to handle automated messaging wor
Provides capabilities for clearing the current conversation state via designated commands to start a fresh session.
MIRIX is an AI agent state orchestrator and long-term memory system designed to provide persistent context for large language models. It functions as a multi-modal AI memory pipeline that processes text, voice, and screen captures into structured knowledge stores, including a dedicated screen activity knowledge base. The project distinguishes itself by integrating a multi-modal observation pipeline that monitors desktop activity in real-time to build a searchable history of user actions. It utilizes a multi-tiered memory hierarchy—separating episodic, semantic, procedural, and core stores—and
Provides capabilities to clear the current conversation dialogue context while preserving long-term agent memories.