baar-core

What it does

I woke up to a $40 bill from an agent that looped overnight on a $5 task. Every solution worked after the call. None stopped the TCP connection. baar-core checks your budget before every API call. Over cap → exception raised locally. No DNS. No TCP. $0 charged. → 84% cost reduction via semantic routing → Per-user SQLite quotas → LangGraph + FastAPI support → MIT licensed pip install baar-core

Hard budget enforcement for LLM agents. Stops API calls before they happen. 84–94% cost reduction. pip install baar-core.

██████╗ █████╗ █████╗ ██████╗ ██╔══██╗██╔══██╗██╔══██╗██╔══██╗ ██████╔╝███████║███████║██████╔╝ ██╔══██╗██╔══██║██╔══██║██╔══██╗ ██████╔╝██║ ██║██║ ██║██║ ██╗ ╚═════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═╝ v0.5.0 · pre-flight budget enforcement for LLM agents Hard local kill-switch. Estimates cost before every request. Budget gone → exception raised locally. No DNS. No TCP. $0 charged. User task │ ▼ ┌───────────────────────────────────────┐ │ Pre-flight budget check │ ← estimated cost > remaining budget? │ (local, zero network calls) │ raise BudgetExhausted — blocked └────────────┬──────────────────────────┘ │ affordable ▼ ┌───────────────────────────────────────┐ │ Semantic complexity router │ ← cheap…from baar.robatdasorvi.com

• 
  Inferock BenchAug 2026 · github.com · ▲295

  Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts. - inferock/inferock-bench

• 
  Tokenomy.ai2025 · tokenomy.ai · ▲105

  See your LLM token bill before you hit send.

• 
  llm-cost-guardJun 2026 · github.com · ▲2

  Stop runaway LLM API spend before it happens

• 
  BursoraJul 2026 · bursora.com · ▲26

  Cap your AI spend before the bill lands

• 
  ProxAI Jul 2026 · proxai.eu · ▲6

  Hard budget caps for LLM APIs — one base_url change

• 
  GateCtrApr 2026 · gatectr.com · ▲2

  Stop LLM bill shock. Budget firewall for any AI API

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 17d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 17d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 19d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 20d ago · stillwet.art

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 29d ago · world.pixverse.video

• 
  Hemory▲381

  Keep listening. Searchable memory for your AI agents.

  AI · 30d ago · hemory.com

• 
  Brew ▲900

  Like Claude design for email marketing

  AI · May 2026 · brew.new

• 
  Kilo Code for VS Code▲896

  Parallel agents, diff reviewer, and multi-model comparisons

  Dev tools · May 2026 · kilo.ai

• 
  StoreClaw▲806

  Grow your store profits with agents that know how to sell

  AI · May 2026 · storeclaw.ai

• 
  PollyReach▲795

  Give your agent a real number and voice to make calls.

  AI · May 2026 · pollyreach.ai

• 
  Needle: We Distilled Gemini Tool Calling into a 26M Model▲776

  Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…

  Life & fun · May 2026 · github.com

• 
  Files.md – Open-source alternative to Obsidian▲730

  🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md

  Dev tools · May 2026 · github.com