Roadmap
This is where agentl is heading. Every item is a GitHub issue: add a
Released
0.1.1 : YAML pipelines, agent steps with validated schemas, per-record cache, connectors
(CSV, JSON, Excel, PDF, Word, HTTP, SQLite), notifications, CLI and local dashboard.
See the changelog .
Next: 0.2, real-world pipelines
Feature
Issue
Read CSV and JSON directly from a URL
#7
Universal file reader: txt, xls, zip/gz, parquet, xml, html, legacy .doc
#22
pandas bridge: steps that receive and return DataFrames
#8
Postgres connectors with upsert
#9
Docs for AI agents: llms.txt, prompt library, AGENTS.md
#10
Guide: migrate a pandas pipeline (CSV over HTTP to Postgres)
#11
Then: 0.3, more sources, providers and operations
Feature
Issue
Remote paths for every reader: SFTP, FTP, SMB, WebDAV, S3, GCS, Azure
#23
Any SQL database: MySQL, SQL Server, Oracle, Snowflake, BigQuery
#24
Email (IMAP) with attachments
#13
Browser connector with Playwright
#14
AWS Lambda connector
#15
More LLM providers: OpenAI, Ollama, Bedrock
#16
Cost budget per run
#17
More notification channels: email, Teams, Discord, Telegram, PagerDuty, Opsgenie
#27
Observability: OpenTelemetry traces and metrics, JSON logs, Sentry
#28
Later
Feature
Issue
Agent tools and MCP servers inside agent steps
#18
MCP server and agentl new to build pipelines from a description
#19
Triggers: schedules, webhooks and file arrivals
#20
Queues and streams: Kafka, RabbitMQ, SQS, Pub/Sub, MQTT
#25
GraphQL and SaaS: Google Sheets, Drive, SharePoint
#26
Cloud integrations: secrets managers, serverless runs, AWS / GCP / Azure services
#29
Missing something?
Open a feature request or a
connector request .
to the ones you need,
comment with your use case, or pick one up and open a pull request.
Priorities change with feedback, so dates are intentionally left out.