KostAI

What it does

LLM FinOps for AI agents: open-source, local-first skills for cost optimization, orchestration, and quality gates. No default telemetry. No default MCP. Proof before rollout.

KostAI is John Bradley's local-first LLM FinOps toolkit for measuring token waste, testing cheaper routes, and preserving frontier escalation for hard work.

KostAI is a local-first LLM FinOps toolkit. It instruments each call, removes context that does not help, routes bounded work to cheaper compute, and keeps hard work on frontier models. I built it—and the systems below—to turn expensive AI ambiguity into measurable engineering proof. Looking for AI platform, solutions engineering, and product engineering roles. KostAI does not rely on one magic trick. It measures the call, removes avoidable input, reuses stable context, and routes only bounded work away from frontier models. The exact mix varies by workload. Prompt caching keeps repeated system instructions and shared context from being billed as fresh work on every call. Deterministic…from kostai.app

• 
  TrueFoundry AI GatewayDec 2025 · truefoundry.com · ▲315

  Many teams connecting LLMs to external tools eventually encounter the same architectural issue: as more tools and agents are added, the integration pattern becomes an N×M mesh of direct connections. Each agent implements its own auth, retries, rate limiting, and logging; each tool needs credentials distributed to multiple places and observability becomes fragmented. We built LLM gateway with this goal to provide a single place to manage authentication, authorization, routing, and observability for MCP servers, with a path toward a more general agent-gateway architecture in the future. The…

• 
  A Karpathy-style LLM wiki your agents maintain (Markdown and Git)Apr 2026 · github.com · ▲260

  I shipped a wiki layer for AI agents that uses markdown + git as the source of truth, with a bleve (BM25) + SQLite index on top. No vector or graph db yet. It runs locally in ~/.wuphf/wiki/ and you can git clone it out if you want to take your knowledge with you. The shape is the one Karpathy has been circling for a while: an LLM-native knowledge substrate that agents both read from and write into, so context compounds across sessions rather than getting re-pasted every morning. Most implementations of that idea land on Postgres, pgvector, Neo4j, Kafka, and a dashboard. I…

• 
  IQ RoutingAug 2026 · iq-routing.com · ▲100

  Route every LLM call to the cheapest model that holds quality. Chatbots, RAG, agent loops, and finance. Cut spend 40 to 80 percent, measured on our own traffic, live in thirty seconds.

• 
  MakeHub.ai2025 · makehub.ai · ▲118

  LLM Provider arbitrage to get the best performance for the $

• 
  OpenBrowser-AIApr 2026 · openbrowser.me · ▲76

  Your AI agent is burning 6x more tokens than it needs to just to browse the web. We built OpenBrowser MCP to fix that. Most browser MCPs give the LLM dozens of tools: click, scroll, type, extract, navigate. Each call dumps the entire page accessibility tree into the context window. One Wikipedia page? 124K+ tokens. Every. Single. Call. OpenBrowser works differently. It exposes one tool. Your agent writes Python code, and OpenBrowser executes it in a persistent runtime with full browser access. The agent controls what comes back. No bloated page dumps. No wasted tokens. Just the data your…

• 
  CostbaseDec 2025 · costbase.ai · ▲6

  Cut LLM Costs 30-80% 2-Minute Setup.

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 19d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 18d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 20d 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 · 22d ago · stillwet.art

• 
  Beam.win▲379

  Run AI agents on one Mac and use its windows on another

  AI · 5d ago · beam.win

• 
  FastRouter.ai▲364

  Route requests to the right LLM for cost, latency & quality

  AI · 23d ago · fastrouter.ai

• 
  Brila▲1,364

  One-page websites from real Google Maps reviews

  AI · Apr 2026 · brila.ai

• AG
  A game where you build a GPU▲964

  Thought the resources for GPU arch were lacking, so here we are

  Life & fun · Apr 2026 · jaso1024.com

• 
  I built a tiny LLM to demystify how language models work▲915

  Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.

  AI · Apr 2026 · github.com

• 
  Fathom 3.0▲800

  AI meeting notes: now bot-free, in ChatGPT & Claude + more

  AI · Apr 2026 · fathom.ai

• 
  Brutalist Concrete Laptop Stand (2024)▲786

  I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay

  Life & fun · Apr 2026 · sam-burns.com

• 
  I built a frontpage for personal blogs▲783

  With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.

  AI · Apr 2026 · text.blogosphere.app