agentleFS
aw3703aw3703/batchin-public/docs/llms-full.txt

batchin-public

llms.txt91 starsChanged 6 months agoApache-2.0View on GitHub

BatchIn Public is the client layer for an evidence-based inference control plane. It contains SDKs, a CLI, an MCP connector, and VaaS verification clients. Provider credentials, customer data, billing ledgers, and hosted route policy stay in the private control plane. Use the authenticated catalog before selecting a model: Only use models whose catalog state reports verified provider smoke, pricing, usage, billing, and account entitlement. Availability can change without a client release. The public repository does not publish a frozen model…

  • Reads credentials
  • Installs packages

The file

We split this llms-full.txt into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the authenticated catalog before selecting a model:

    line 9
  2. Distinctive:

    Only use models whose catalog state reports verified provider smoke, pricing, usage, billing, and account entitlement.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms-full.txt
# BatchIn Developer Reference

## Scope

BatchIn Public is the client layer for an evidence-based inference control plane. It contains SDKs, a CLI, an MCP connector, and VaaS verification clients. Provider credentials, customer data, billing ledgers, and hosted route policy stay in the private control plane.

## Discover before calling

Use the authenticated catalog before selecting a model:

```bash
curl https://api.batchin.tech/v1/models \
  -H "Authorization: Bearer $BATCHIN_API_KEY"
```

Only use models whose catalog state reports verified provider smoke, pricing, usage, billing, and account entitlement. Availability can change without a client release. The public repository does not publish a frozen model matrix or prices.

## OpenAI-compatible requests

For supported routes, set the client base URL to `https://api.batchin.tech/v1` and use a model ID returned by the catalog. Compatibility is route- and model-specific. Unsupported parameters, unavailable models, insufficient balance, and provider failures are returned as structured errors.

```python
from batchin import BatchIn

client = BatchIn(api_key="your_batchin_api_key")
models = client.models.list()
model_id = models["data"][0]["id"]
result = client.chat.completions.create(
    model=model_id,
    messages=[{"role": "user", "content": "Hello BatchIn"}],
)
print(result)
```

Multimodal and asynchronous media routes have separate contracts and require an enabled route, output asset, usage record, cost record, and billing record.

## Package map

| Package | Purpose |
| --- | --- |
| `@batchin/sdk` | TypeScript API client, streaming, model discovery, and usage metadata |
| `@batchin/ai-sdk` | Vercel AI SDK provider adapter |
| `batchin` | Python API client and adapters |
| `@batchin/cli` | Authenticated API checks and model discovery |
| `batchin-mcp-server` | MCP catalog, inference, pricing, trace, and receipt tools |
| `@batchin/vaas` | TypeScript receipt and evidence verification client |
| `batchin-vaas` | Python receipt verification client |
| `@batchin/contracts` | Public VaaS Solidity interfaces; deployment is environment-gated |

## VaaS and payments

VaaS verification accepts a real receipt bundle and checks its evidence. Test fixtures are useful for client tests but must be labeled as fixtures. Chain anchoring, x402, USDC, Stripe checkout, refunds, and settlement are readiness-gated; inspect API readiness and ledger records before using those paths in a product.

```bash
npx @batchin/vaas verify <receipt-file-or-record-id> \
  --endpoint https://api.batchin.tech
```

## MCP

Install the connector with `pip install batchin-mcp-server`. The server exposes only the tools registered by the installed package and forwards API errors. Configure the API key through the MCP process environment; never commit it to a client configuration or issue.

## Local checks

```bash
npm ci
npm run typecheck
npm run build
npm run test:ts
npm run test:py
npm run compliance
```

These checks validate client packages and policy scans. They do not perform provider, payment, or chain smoke against production.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.