vstorm-co/summarization-pydantic-ai
Context Management processor for Pydantic AI agents, providing LLM-powered summarization or zero-cost sliding window trimming to handle infinite/long-running conversations without context overflow. Supports flexible triggers, safe cutoffs, and custom prompts for efficient AI apps.
Implements both **Capabilities API integration** (auto-detects model context windows) and **standalone Processor API** for flexible deployment with Pydantic AI. Features real-time token counting via `tiktoken`, intelligent tool output truncation that preserves call/response pairs, and configurable triggers (message count, token count, or context fraction) with multiple keep strategies to balance compression quality against latency and cost.
10 stars and 71,066 monthly downloads. Available on PyPI.
Stars
10
Forks
2
Language
Python
License
MIT
Category
Last pushed
Feb 27, 2026
Monthly downloads
71,066
Commits (30d)
0
Dependencies
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/vstorm-co/summarization-pydantic-ai"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
brain-tree-dev/brain-tree-os
Open source brain viewer and project management for AI agents. Give your AI a brain.
Fozikio/cortex-engine
Cognitive engine for AI agents — semantic memory, observations, embeddings, dream consolidation....
NateBJones-Projects/OB1
Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat...
hyperb1iss/sibyl
Collective intelligence runtime for AI agents. Knowledge graph + orchestration + persistent memory.
inputlayer/inputlayer
Streaming reasoning layer for AI. Incremental rules engine with vector search, graph traversal,...