# parcadei/Continuous-Claude-v3

Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.

Repository: https://github.com/parcadei/Continuous-Claude-v3
Canonical: https://ross.abutalabs.com/products/continuous-claude-v3
Language: Python
License: MIT
License Family: permissive
Topics: agents, claude-code, claude-code-cli, claude-code-hooks, claude-code-mcp, claude-code-skills, claude-code-subagents, claude-skills, mcp
Last push: 2026-01-26T15:27:49+00:00

## Health v2 (maintenance only)
Score: 45/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 64, release rhythm 35, longevity 18
- inputs: {"age_days": 254, "days_push": 219, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3930, forks 298 (observed 2026-08-28T04:08:29.961838+00:00)

## What it is
A framework that turns Claude Code into a persistent, multi-agent development environment with context management across sessions. It uses hooks, YAML handoffs, ledgers, 109 skills, 32 specialized agents, and a memory daemon to avoid context compaction and token waste.

## Use cases
- maintain Claude Code context across sessions
- avoid losing context when Claude Code compacts
- orchestrate multiple Claude Code subagents
- run MCP tools without polluting context
- automatically extract learnings from coding sessions
- reduce token usage when analyzing large codebases
- set up reusable skills with natural language triggers

## When to choose
- you use Claude Code daily and hit context compaction limits
- you want persistent memory and learnings across coding sessions
- you need multi-agent orchestration with isolated context windows
- you want to reduce token spend on repetitive code analysis

## When to avoid
- you don't use Claude Code or Claude models
- you need a simple single-session assistant without state
- you prefer minimal setups without hooks and daemon processes
- you need a vendor-neutral agent framework

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, mcp, prompt-engineering, developer-tools, workflow-automation
- domain: developer-tools, large-language-models
- platform: cli, python, cross-platform
- tags: claude-code, context-management, hooks, subagents, skills, memory-system, session-continuity, token-efficiency, ai-agents, automation

## Member repositories
- parcadei/Continuous-Claude-v3 (main) score 45

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:29.961838+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:24:41.835244+00:00, confidence not recorded.
  - readme: https://github.com/parcadei/Continuous-Claude-v3 (fetched 2026-08-28T04:08:29.961838+00:00, sha 07f11bd138b1)
- Data as of 2026-08-30T08:39:29.467469+00:00.