keywords:token-limit

llm-spend-guard

Enforce real-time token budgets and spending limits for OpenAI, Anthropic Claude, and Google Gemini API calls in Node.js

ali_raza_arain

published version 2.0.6, 2 months ago0 dependents licensed under $MIT

321,890

llm-info

Information on LLM models, context window token limit, output token limit, pricing and more

paradite

published version 1.0.69, 6 months ago7 dependents licensed under $MIT

35,949

@purpleraven/hits

Your AI session died. Your work didn't. The checkpoint system for AI coding sessions — token limits, session swaps, tool switches, pick up where you left off.

purpleraven

published version 1.3.7, a month ago0 dependents licensed under $Apache-2.0

392

@monetisebg/circuit-breaker

Circuit breaker for AI agents — pick budget-guard or loop-killer mode and stop runaway token spend or stuck agents in one wrapper. Adapters for LangChain, OpenAI Agents SDK, and the Claude Agent SDK.

monetisebg

published version 0.1.1, 18 days ago0 dependents licensed under $Apache-2.0

249

@loret/sdk

Runtime policy layer for LLM applications — enforce cost, privacy, and runtime guardrails on every model call

micheale

published version 1.1.1, a month ago0 dependents licensed under $MIT

274

jasper-context-compactor

Context compaction plugin for OpenClaw - works with local models (MLX, llama.cpp) that don't report token limits

e-x-o-studio

published version 0.4.1, 4 months ago0 dependents licensed under $MIT

118

context-weaver

Smart, persistent context memory for RAG applications. Stop managing chat history arrays manually.

srikrish

published version 1.0.1, 6 months ago0 dependents licensed under $MIT

43

@storepress/llm-md-text-splitter

High-performance streaming Markdown text splitter for LLM pipelines and RAG systems. Zero sequence loss for code blocks, tables, links, and videos. 5 built-in strategies + custom. Zero dependencies.

emran

published version 0.0.1, 4 months ago0 dependents licensed under $MIT

20

@mcp-proxy/intercept

Transparent MCP sidecar proxy. Intercepts JSON-RPC traffic, analyzes payloads in real-time, and shows you exactly what vurb.ts would fix — without changing your code.

vinkius

published version 1.0.0, 3 months ago0 dependents licensed under $Apache-2.0

25

@mcp-doctor/diagnostics

Diagnostic interceptor for raw MCP servers. Detects architectural flaws in real-time and prescribes the fix.

vinkius

published version 1.0.1, 3 months ago0 dependents licensed under $Apache-2.0

27

smart-data-pruner

Smartly prune massive JSON/strings for LLM context optimization with cost estimation.

ritesh17rb

published version 1.0.1, 5 months ago0 dependents licensed under $MIT

19

@bantai-dev/llm

Policy & governance for AI & LLM usage

jun-paul.i.bosque

published version 1.0.0, 4 months ago1 dependents licensed under $MIT

17

agent-cost-guardrails

Budget limits and cost guardrails for AI agents. Prevents runaway API spend with hard budget enforcement, circuit breakers, and per-agent cost tracking.