Agentcents

io.github.labham-llcPublished by GitHub account labham-llcv1.1.3Updated Oct 24, 2026

Local LLM cost proxy: forecasts each call and recommends the cheapest model that clears the task.

VerifiedSTDIODesktop onlyFinanceAI & ML

Overview

AI-generated overview

A local LLM cost advisor that estimates what a call or agent workflow would cost and recommends the cheapest model that clears the task's capability bar.

What you can do
Agentcents acts as a local LLM cost proxy and consulting skill: it forecasts the cost of a call or multi-step agent workflow across candidate models, compares them, and picks the cheapest model that meets the task's capability bar. It presents comparisons as Mermaid diagrams and reports honest ranges rather than false point estimates. In consult mode it answers from a bundled snapshot of model prices and Intelligence Index scores; in live mode, when the local agentcents proxy is running, it uses the user's real ledger with calibrated forecasts, spend, and accuracy.
When to use it
Useful when planning or budgeting LLM usage: estimating the cost of a workload such as classifying a batch of support emails, or deciding which model each step of a multi-step agent should use. It suits people who want a neutral, cost-aware model recommendation before committing to an API spend.
Requirements
Runs as a local process on the user's machine (desktop only, not web-executable), installed from the PyPI package agentcents over stdio. No authentication, environment variables, or headers are declared. Live mode requires the agentcents proxy to be running locally; consult mode works without installing the proxy.
Before you install
Live mode reads the user's real ledger from a locally running agentcents proxy, so it depends on that local service being present and trusted. The bundled price and capability snapshot is dated and refreshed only with agentcents releases, so figures can go stale. The agentcents software itself is proprietary, while the skill instructions and snapshot data may be redistributed with attribution.

Installation

In SourceWeft

  1. Open Agentcents in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

agentcents — LLM cost consulting skill for Claude

A Claude Skill that turns Claude into a neutral LLM cost advisor: estimate what any call or agent workflow will cost across candidate models, get the cheapest model that clears the task's capability bar, and see the comparison as a Mermaid diagram — with honest ranges, never false point estimates.

Works two ways:

  • Consult mode (no install): answers from a bundled, hand-verified snapshot of current model prices and Intelligence Index scores.
  • Live mode: if the agentcents proxy is running locally, the skill uses your real ledger — calibrated forecasts, spend, and accuracy instead of priors.

Install

Claude.ai / Desktop: Settings → Capabilities → Skills → Add → upload this folder (or the packaged .skill).

Claude Code: /plugin marketplace add labham-llc/agentcents-skill then /plugin install agentcents@labham-skills

Then just ask things like:

what would it cost to classify ~500 support emails a day, about 200 tokens each?

I'm building a 5-step research agent — which model should each step use?

What's in the box

SKILL.md                 — the consulting method (measure, range, bar, pick, flag instability)assets/pricing.json      — price + capability snapshot (see _meta.verified_utc)references/local-api.md  — live-mode reference for a locally running agentcents

Snapshot verified: 2026-07-15 (see _meta.verified_utc) — refreshed with each agentcents release.

The product behind it

agentcents is a local proxy that meters, forecasts, and budget-enforces LLM API calls — and grades its own forecasting accuracy on a calibration page. pip install agentcents. The skill is free; so is the agentcents free tier.

© Labham LLC · skill instructions and snapshot data may be redistributed with attribution; the agentcents software itself is proprietary (see its LICENSE).

Source: README.md at commit 5f52390

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.1.3LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.