dgenio/contextweaver
Budget-aware context compilation and context firewall for tool-heavy AI agents.
Implements an eight-stage context compilation pipeline that selectively includes events, tool schemas, and dependencies based on per-phase token budgets, combined with a routing engine that beam-searches a bounded DAG of tool catalogs to generate compact choice cards. The architecture uses protocol-based storage backends (event logs, artifact stores, episodic memory) for flexibility, integrates with MCP and A2A agentic standards, and includes a context firewall that externalizes large tool results while injecting summaries into prompts—all deterministic, zero-dependency, and fully instrumented with per-build diagnostics.
Available on PyPI.
Stars
3
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 10, 2026
Monthly downloads
853
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/dgenio/contextweaver"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
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.
onfabric/context-use
Turn your data exports into portable AI memory.
EfficientContext/ContextPilot
Accelerating Long Context LLM Inference with Accuracy-Preserving Context Optimization in SGLang,...
LogicStamp/logicstamp-context
A Context Compiler for TypeScript. Deterministic, diffable architectural contracts and...