danielckv/ContextLoom
ContextLoom is the shared "brain" for multi-agent systems. It weaves together memory threads from frameworks like DSPy and CrewAI into a unified, persistent context, powered by Redis and hydrated from your existing databases.
Decouples memory from compute by maintaining a shared Redis-backed context state that persists across framework boundaries, with automatic "cold start" hydration from PostgreSQL, MySQL, or MongoDB. Introduces cycle-aware state management using hash-based loop detection to prevent agent repetition and ensure goal progression. Provides native adapters for DSPy, CrewAI, Agno, and Google ADK, enabling cross-framework context sharing without manual state injection.
Stars
31
Forks
—
Language
Python
License
—
Category
Last pushed
Dec 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/danielckv/ContextLoom"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ultracontext/ultracontext
Open Source Context infrastructure for AI agents. Auto-capture and share your agents' context everywhere.
dunova/ContextGO
Local-first context & memory runtime for multi-agent AI coding teams. MCP-free. Rust/Go accelerated.
dgenio/contextweaver
Budget-aware context compilation and context firewall for tool-heavy AI agents.
EfficientContext/ContextPilot
Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang,...
onfabric/context-use
Turn your data exports into portable AI memory.