A visual, editable context management panel for Codex. Better context compression, smarter compression strategies, automatic context organization suggestions, and system prompt…
#context-management
MCP servers, skills and plugins tagged “context-management” on GitHub.
44 entries · real GitHub data
- #32Zero Drift
Keeps AI assistants on track during long conversations by tracking tasks across sessions
Convert long AI conversations into portable conversation state graphs for LLM handoffs.
Restore prior Claude Code AND Codex sessions with zero LLM calls. Cross-tool session handoff, cache-expiry prevention, real cost dashboard. One plugin, both hosts.
Built-in memory decides what to remember. This one asks. Agent memory as plain files in your folder: the agent proposes, you approve, every line dated. Injected on Claude Code,…
Rolling context compression for Claude Code — never hit the context wall. Auto-compresses old messages while keeping recent context verbatim. Zero config, zero latency. Works…
- #37Fava Trails
FAVA Trails — Git-native, curated memory for AI agents via MCP. Draft isolation, promotion gate, thought lifecycle hooks, memory curation protocols, supersession chains.
- #38Aigent Os
Claude Code harness that refreshes its own context instead of compacting: at a threshold it writes a verified capsule, runs /clear, and resumes in a fresh session. Memory is…
Maintain the same context between AI chats, models, and coding agents. Stop re-explaining your project every time you switch AI tools.
- #40Claude Pilot
Claude Code workflow engine - SPEC-first planning, TDD automation, GPT delegation, and context engineering. From idea to production, discipline included.
A powerful CLI to orchestrate workspaces and dynamically inject specialized skills into AI coding agents.
Persistent memory for Claude Code. Auto-capture decisions, learnings, client info. Cloud backup to Supabase. Never lose context again. Free alternative to Mem.ai, Rewind AI,…
- #43Pluribus
Sync one reviewed context source into native AI-agent files, with privacy-safe evidence receipts that never confuse generation with runtime load.
Turn long AI conversations into reusable domain knowledge across sessions