fil.one valid

Automatically discovered from public files. Ownership management is optional. Inclusion does not imply endorsement or publisher participation.

Manage this listing — optional · Visit publisher ↗

Claim my listing on Agent Web Map for fil.one:
1. POST https://agentwebmap.com/v1/sites/fil.one/claims and keep claim_id and claim_secret private.
2. Publish the proof: add the line "AgentWebMap ownership: <token>" (token from step 1) to https://fil.one/llms.txt, or use the DNS, meta-tag or well-known method the response describes.
3. POST https://agentwebmap.com/v1/sites/fil.one/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/fil.one).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verify

Corrections or removal requests: contact the directory. Ownership management is optional.

Fil One

Fil One is the storage layer for AI agents. S3-compatible object storage built

Their llms.txt

The beginning of the file, from our validated copy saved 2026-10-21T01:34:39.624Z. Cached copy · Source on fil.one

# Fil One

> Fil One is the storage layer for AI agents. S3-compatible object storage built
> on Filecoin, designed for the data patterns of autonomous agents: high-frequency
> writes, large retrieval sets, and long-lived persistence.
> Flat pricing at $5.99/TB/month. No egress penalties. No per-request charges.
> Free 30-day trial, no credit card required.

## Why AI agents use Fil One

AI agents need durable, cost-predictable storage for the artifacts they produce and
consume. Fil One is optimized for these workloads:

- **RAG / vector store document corpus:** store and retrieve the raw documents,
  chunked text, or embeddings backing a retrieval-augmented generation pipeline
- **Agent memory and state:** persist conversation history, episodic memory, task
  queues, and checkpoint files across agent restarts
- **Model artifacts:** host fine-tuned weights, GGUF/ONNX model files, LoRA
  adapters, and tokenizer configs that agents load at runtime
- **Inference inputs and outputs:** archive prompts, completions, traces, and
  structured outputs for evaluation, fine-tuning, or audit
- **Training and evaluation datasets:** store JSONL, Parquet, or HDF5 datasets;
  read them back as often as you need with no egress cost
- **Tool / plugin asset storage:** back a code-interpreter sandbox, image
  generation pipeline, or document-processing tool with persistent file storage

## How to connect

Fil One is a drop-in S3 replacement. No SDK changes required: point any existing
S3 client at the Fil One endpoint:

- **Endpoint:** `https://s3.eu-west-1.filonecontent.com`
- **Region:** `eu-west-1` (Europe, France; default). `us-east-1` (US East, Michigan)
  is also available at `https://s3.us-east-1.filonecontent.com`
- **Auth:** standard AWS Access Key ID + Secret Access Key
- **Addressing:** path-style only; virtual-hosted-style is not supported

### Python (boto3)

```python
import boto3

s3 = boto3.client(
    "s3",
    endpoint_url="https://s3.eu-west-1.filonecontent.com",
    aws_access_key_id="YOUR_ACCESS_KEY",
    aws_secret_access_key="YOUR_SECRET_KEY",
    region_name="eu-west-1",
)

# Upload an agent checkpoint
s3.upload_file("checkpoint.json", "my-agent-bucket", "checkpoints/run-42.json")

# Retrieve a RAG document
obj = s3.get_object(Bucket="my-agent-bucket", Key="corpus/doc-001.txt")
text = obj["Body"].read().decode()
```

### Node.js (@aws-sdk/client-s3)
…

Related sites

Other listed sites in AI and machine learning. See the whole category →

Help agents understand your site

Optionally manage your description, publish terms for agents, review file health, measured discovery requests, publisher clicks and score history. Confirm domain control in your browser using a fresh token in your llms.txt, DNS, meta tag or well-known file. No backlink is required.

Manage this listing → · Agent and API instructions

Machine-readable: GET /v1/resolve?q=fil.one · GET /v1/domain/fil.one · this page as Accept: application/json or text/markdown · MCP lookup_domain