A circuit breaker for your LLM API bill — hard budget caps + per-feature cost attribution for the OpenAI & Anthropic APIs.

DSH plugin for AST context compression, test log filtering, and token budget guard

The stateful half of SignalScout: monitors, posts, matches, cursors, the budget guard and the jobs, with their migrations.

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

Turn budget guard for dsh: caps the number of steps one agent turn may spend before the model is asked to wrap up, then stops the turn. Closes the 'no ceiling on action' gap measured in Discussion #6366 (33-50 turns / 32-70 tool calls for a one-field conf

DeepSeek Harness plugin: LLM cost metering with budget enforcement (deny/warn), peak-valley pricing and a live usage dashboard

Batch task pipeline for DeepSeek Harness: a cross-session batch ledger with progress pointer, budget guard, and product assertions — model-facing tools plus a per-step progress injection.

Runtime budget, action, and audit authority for OpenClaw agents — enforce LLM cost limits, tool call caps, and audit trails before execution.

Control token usage before expensive AI API calls

Anonymous public HTTP(S) fetch provider for the DeepSeek Harness web capability seam (ctx.web)

Tool-call timeout policy: a tools/execute wrapper that arms a per-tool deadline on exec.signal and returns TOOL_TIMEOUT when it wins

x402 payment engine, service registry, and budget guard for Stellect

Model-facing web tools (web_search, web_fetch) over the DeepSeek Harness web capability seam (ctx.web)

LLM API budget enforcement with real-time cost tracking, automatic model downgrade, and spending limits

The task state machine at the core of Sockt's anti-runaway design. A SQLite-backed `TaskStore` implementation, a strict finite state machine that enforces valid task transitions, an LLM-call budget guard, and an atomic claim lock for concurrent agent work

Local-first LLM usage & cost tracker. Wrap your OpenAI/Anthropic/Gemini client in one line to measure tokens, cost, latency and per-feature spend — with a budget guard and a local dashboard. Zero exfiltration, zero runtime deps in the core.

OCI NodeJS client for Budget Service

Per-task budget, loop detection, and kill-switch middleware for agent LLM calls. v0, deterministic and dependency-free.

An extension for Pi coding agent that tracks session spend and enforces budget limits.

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