Give your AI agents
shared memory.
An open protocol built on attunement ~ where agents declare who they are, and the right context finds them automatically.
Compatible with MCP and A2A · Progressive adoption from Level 0 to 3 · Open specification
The Problem
Our agents can call tools.
They can talk to each other.
But they can't remember.
They can't share what they know. And when two agents contradict each other, there's no standard way to catch it.
Every multi-agent system today carries its own ad-hoc memory layer ~ bespoke, fragile, and non-interoperable. Akashik is the protocol that replaces it.
Where it fits
MCP handles agent-to-tool. A2A handles agent-to-agent. Akashik handles what they share, how they stay coordinated, and how they resolve contradictions.
What makes it different
Intent is mandatory.
You cannot write to the Field without declaring why. Every finding carries the question it answers. You get a reasoning chain for free.
Attunement, not search.
Agents declare who they are ~ role, task, budget. The Field figures out what's relevant and delivers it. Context finds the agent.
Conflicts are expected.
When agents contradict each other, Akashik detects it and gives you structured resolution paths ~ from last-write-wins to human escalation.
v0.2 · write, reckon, resolve
import { createField } from '@akashikprotocol/core'
const field = createField()
await field.register({ id: 'researcher', role: 'researcher' })
await field.register({ id: 'fact-checker', role: 'researcher' })
// Intent is mandatory — the why, not just the what
await field.write({
entry: { topic: 'pricing', price: '$49/mo' },
intent: 'competitor pricing observed on G2',
agent: 'researcher',
})
await field.write({
entry: { topic: 'pricing', price: '$39/mo' },
intent: 'corrected after verifying the competitor site directly',
agent: 'fact-checker',
})
// reckon = attune + conflict detection
const result = await field.reckon({ agent: 'writer', topic: 'pricing' })
console.log(result.conflicts)
// [{ keys: ['price'], a: researcher entry, b: fact-checker entry }]
// The protocol surfaces the disagreement. You decide what to do. Two agents. One conflict. reckon surfaces it. You decide what to do with it.
Progressive adoption
Start with Level 0 in an afternoon.
Grow to production-grade when you need it.
REGISTER, RECORD, ATTUNE. In-memory. No embeddings.
~ an afternoon · v0.2 releasedDEREGISTER, RETRACT, SUPERSEDE, DETECT. Conflict detection ships in v0.2. Persistence and clocks in v0.3.
~ a week · partial in v0.2Semantic attunement, MERGE, push subscriptions, REPLAY.
~ serious buildSecurity model, authority hierarchy, coordination extension.
~ production-grade