Validation gates, plan checks, and token-budget guardrails for AI coding agents.

OpenCode plugin for token-budget guardrails: counts budgeted tool calls, injects reminders at thresholds, audits usage automatically, and makes session handoff a single tool call

TanStack AI middleware for context-chef. Transparent history compression, tool result truncation, and token budget management.

Audit LLM prompt files for token waste and enforce a token budget in CI.

MCP server: static worst-case token-budget analysis for LLM-agent workflows (LangGraph/CrewAI/OpenAI-Agents) + signed budget certificates.

Strict token budget context builder and compression engine for MemoryAI

Token budget linter for agent skill files

Keep long-running AI agents — coding agents, autonomous agents, tool-calling loops — inside their context window: pluggable eviction/summarization strategies, atomic tool-call preservation, cost accounting, and an explain() trace, for any model or framewo

Shrink long prompts to hit a token budget and expand them back exactly — the same input always produces the same output.

MCP 服务器 — 把 token-budget 核心能力暴露给所有支持 MCP 的客户端（Claude Desktop / Cursor / Trae / Cline / DSH 等）

No-summary context-window rollover for Pi with durable notes checkpoints, history recovery, and a post-fallback tool-call fence.

Constant-size memory for long-form AI writing. Chapter 1000 gets the same token budget as chapter 10. Zero dependencies, runs anywhere JS runs.

MCP server for token-budget-aware text truncation. Helps an LLM fit text into a context window mid-task.

Token budget analyzer for AI context windows — like du for tokens

Truncate strings to a token budget without cutting mid-token or mid-character. Provider-agnostic with adapter support.

Fit a prompt into the model's token budget — add your messages and context, pin what must stay, and the least-important parts are dropped to make it fit.

Truncate strings to a token budget without cutting mid-token or mid-character. Provider-agnostic with adapter support.

Token budget management — estimate and optimize token usage for AI agents.

Pack a repo into LLM-ready context — git-diff-aware and token-budget-aware, unlike full-dump tools.

[EXPERIMENTAL / PRE-RELEASE] Session token budget guard for DeepSeek Harness: per-session token accounting with an automatic task interrupt at the configured cap.