01 / 03

Anything a laptop does,an agent can run.

Drag agents, tools, and models onto a canvas. Wire them with arrows. Schedule, run, replay. Research, ops, reporting, outreach. Anything an LLM can reason about, an agent runs alongside your team.

← Back to home
0scoped tools . ten supercategories
subagents111+models15+ providers
·MELAYA·v2026.06

One canvas. Every workflow.

A daily treasury briefing in your inbox at 7am. A deal-flow screener that reads pitch decks and shortlists three. A risk alert that pages on-call when a Slack channel spikes. A board update drafted from real filings, not vibes. Each one is a small team: a researcher, an analyst, a writer, a reviewer. You hire from 111 prebuilt personas, brief each in plain English, scope what they're allowed to touch, and wire their handoffs on the canvas. The org chart is the program, and the canvas runs the meeting.

The catalog grows every month.

1912toolsscoped per step
111+subagent templatesfork . edit . share
RESEARCH & KNOWLEDGE. 5401/10
GEO, TRAVEL & WEATHER. 3902/10
TRADING & FINANCE. 3603/10
GOVERNMENT & OPEN DATA. 3604/10
PRODUCTIVITY & SAAS. 3605/10
DEV & INFRASTRUCTURE. 3306/10
COMMUNICATIONS. 3007/10
MEDIA & CULTURE. 2408/10
NEWS, WEB & SEARCH. 2109/10
SOCIAL & COMMUNITY. 1810/10

Tools are the actions an agent can take in the real world: send an email, read a CRM record, fetch the weather, post to Slack. Each agent only gets the ones you hand it.

Drag, pin, chain, ship.

Every pipeline is four primitives. Steps, tools, subagents, edges.

DRAGtool chip onto a step
PINmodel per step
CHAINedges feed next context
SHIPsave persists to project

The model picker sits on every step. Claude, GPT, Gemini, or a local Ollama on your own runner. Mix providers inside one pipeline.

Anthropic
DRAFTER
research . subagent
model Anthropic
tavilyserppy
Ollama
CRITIC
score . subagent
model Ollama
pypost
OpenAI
REPAIRER
ship . subagent
model OpenAI
pygithub

What every step gets, for free.

Three channels for memory. One channel for the human.

  • Static context . pin docs, schemas, policies into the prompt
  • Per-workflow RAG . your files, urls, prior runs. Index ties to the pipeline, not the user
  • Cross-run memory . the same crew sharpens each cycle without re-prompting
  • HITL gate . drop the shield on a tool. Pipeline pauses for a human one-click
ANALYST
scope . step
tavilyserppypost
static . rag . cross-run . hitl

Pipelines, keys, runs. Shared by default.

Every pipeline lives in a project. Your team shares one canvas, one set of connectors, one run history.

Connectors are project-scoped. The owner sets a key once, every pipeline inherits it. Rotate once, every run picks up the new credential. Owners decide who joins, who edits, and who only watches. Invite by username, or by a shareable link with an expiry.

  • scopeproject . pipeline . tool
  • connector sharingowner sets . editors use
  • rolesowner . editor . viewer
  • inviteusername or shareable link
OWNERinvites
EDITORbuilds
VIEWERwatches
PROJECTfinance-team
pipelines
12
connectors
5
runs / wk
84
AnthropicGitHubSlackMelaya

Cron. Webhook. API. SSO.

cron
0 */4 * * *
webhook
/v1/run/abc
api
POST /v1/run
sso
event.received
T-7dgpt
T-3dsonnet
T-1dgpt
T-4hollama
T-12msonnet

Diff two runs side by side. Feed a replay back as a regression test.

trigger types4
concurrent lanes1 to 50
runs / mo Citadel5 000
replay windowfull history
morning-brief
running . 1m 02s
daily-outreach
paused . HITL . HITL
weekly-recap
scheduled . next in 03:14
"Anyone can build agents.
Build your first pipeline."
Join the community
// Cookies
Melaya uses a small set of first-party cookies that are strictly necessary to authenticate you, maintain your session, and protect the platform from abuse. We do not use advertising cookies, cross-site trackers, or third-party analytics by default. The full cookie list is in our Privacy Policy.