continuous-claude
A setup that improves context management for Claude Code using hooks, ledgers and handoffs to keep state between sessions, plus agents that run in isolated context windows.
Share on XLicense: MIT
Overview
Continuous Claude is a development setup built on Claude Code that keeps context across sessions. Claude Code compacts the conversation when context fills up, which can lose decisions made earlier. This project uses hooks, ledgers and handoffs to hold state between sessions, and runs specialized agents in isolated context windows. It also adds MCP execution without context pollution, a memory system and token-saving code analysis.
Key features
- Hooks keep state through ledgers and handoffs
- Agents orchestrated in isolated context windows
- MCP execution that avoids polluting context
- Memory system and TLDR code analysis to save tokens
Best for
Heavy Claude Code users who lose track of decisions when context is compacted and want a persistent, multi-agent workflow. It is a large setup, so expect some configuration effort.
- Upstream
- parcadei/Continuous-Claude-v3
- Fork on GitHub
- Guo-astro/continuous-claude
- Upstream stars
- 3.9k
- Category
- AI agents and LLM tools
- Language
- Python
- License
- MIT
- Forked
- 2025-12-25
- Sync status
- In syncLast synced 2026-09-29
More in AI agents and LLM tools
A free desktop app where children in non-English-speaking countries practice English speaking and listening by talking with an AI companion. It can run locally and offline.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub
An agent skill for Chinese patents. It helps find patentable points, write disclosure documents, explain patents in plain language, follow policy changes and assist with examination replies.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub
A minimal Python library from Hugging Face for building AI agents that write and run code to solve tasks. It lets you set up capable agents in a few lines.
Forked 2026-09-28Last synced 2026-09-29License: Apache-2.0AI agents and LLM toolsGitHub
An open-source benchmark that measures how well AI agents handle realistic legal work. It provides tasks and evaluation for improving legal agents.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub