Token Budget Python Packages

contextpress

Deterministic context compression for LLM chat, RAG, and agent pipelines

agent-tokenops

Run-aware token governance for multi-agent systems.

veronica-core

Runtime containment kernel for LLM agents. Enforces budget, step, retry, and circuit-breaker limits before the model call.

ectype-cli

Read, filter, redact and export the on-disk sessions of ten AI coding agents (Claude Code, Codex CLI, Gemini CLI, Antigravity, Copilot Chat, Cursor, Cline, Roo Code, Continue, Aider) and three chat apps (LM Studio, Open WebUI, SillyTavern), or copy one back into its agent and resume it. Command line and a local web UI.

ctxbudgeter

ContextOps toolkit for production AI agents. Compile, govern, scan, visualize & optimize LLM context before every model call — token budgets, policy governance, PII/secret scanning, Context Bill of Materials, diffing, Context MRI, MCP budgeting. Framework-agnostic. Local-first. Deterministic.

cognitive-cache

Context window selection for LLM coding tools. Treats context as a constrained optimization problem, not retrieval.

contextcram

llm · rag · context-window · tokens · prompt-engineering · token-budget · agents · python

contexttrim

Pluggable context window management strategies for LLM agents. Zero dependencies.

hermes-context-tuner

See what your Hermes agent's context compressor actually threw away. Audit trail, token-budget planning, and recovery pointers — no patching, no forking.