The missing layer — v0.2.0 · Apache 2.0

AI agents can talk. They can pay. They can't yet negotiate.

In the next 24 months, a growing share of B2B procurement, renewals, and supplier negotiations will run agent-to-agent. Pactum already negotiates for Walmart and Maersk. But when two agents from different companies meet, there is no neutral protocol for them to commit on terms — no shared offer format, no way to verify the other side has authority, no tamper-evident record of what was agreed. A2CN is that layer.

See it in action → Read the spec
B2B
Agent negotiation is already appearing in procurement — but current systems are closed and buyer-side
3
Adjacent protocols exist: MCP, A2A, AP2. None covers commercial negotiation across organizational boundaries.
0
Open, neutral standards for how agents safely commit to binding commercial terms today.
Explore the protocol

Three ways to understand what A2CN does.

Scrub the timeline to see why now is the right moment. Run a live negotiation between two agents. Or wire it into a real procurement platform and see the adapter output change.

The negotiation layer needs to exist now.
Agent protocols have been converging on this gap for three years. A2CN fills it.
2022
Procurement negotiation agents enter production
AI agents begin negotiating tail-spend contracts for large enterprises. Proof the category exists. Closed platform; buyer-side only.
2024
Anthropic ships MCP
Agent-to-tool communication becomes a standard. Agents can now reliably call APIs and use structured tools — the plumbing layer.
2025 · spring
Google ships A2A
Agent-to-agent communication becomes a standard. Agents can discover each other and delegate tasks. But still no commercial layer.
2025 · fall
AP2 and ACP emerge
Agent payment execution gets standardized. Now agents can move money. The stack has talk, discover, pay — and a hole where negotiation should be.
2026
A2CN v0.2.0 — you are here
Open, neutral protocol for commercial negotiation between agents from different organizations. 8 components, 300+ tests, Fairmarkit + Keelvar + Salesforce adapters, MCP server, A2A extension proposal submitted.
next
Neutral record custody
Optional third-party custody for completed transaction records, so neither negotiating party controls the only durable copy.
Watch a bilateral SaaS renewal negotiation.
Two agents. Different organizations. Neither controls the authoritative record — the cryptography does.
Ready
T
TechCorp Buyer Agent
did:web:techcorp.com
✓ Mandate verified
A
Acme Seller Agent
did:web:acme.io
✓ Mandate verified
Dual-signed transaction record generated independently by both parties
final terms SaaS renewal · $105,000 · net-45
buyer hash —
seller hash —
match ✓ identical — cryptographically binding on both sides
Drop A2CN into a procurement platform.
Zero platform changes. Adapters translate webhook events into A2CN sessions and agreed terms back into response format.
$1.80M
14 days
adapters/fairmarkit_adapter.py event: BID_CREATED
Where A2CN fits

The agent stack has three layers. A2CN is the fourth.

MCP — Agent-to-tool ✓ Exists Model Context Protocol — tools, resources, prompts A2A — Agent-to-agent communication ✓ Exists Google Agent-to-Agent — task delegation, capability discovery A2CN — Commercial negotiation ← this layer Offer exchange · Mandate verification · Dual-signed record AP2 / ACP — Payment execution ✓ Exists Agentic Payment Protocol / Agent Commerce Protocol — settlement

Agents can talk. Agents can pay. Agents cannot yet safely negotiate commercial terms across organizational boundaries.

Eight protocol components

What the spec actually covers.

Each component solves a specific problem that shows up the moment you try to wire two agents from different companies together to commit on a deal.

01
Discovery
/.well-known/a2cn-agent — agents advertise capabilities and find each other without a central registry
02
Mandate verification
Cryptographic proof an agent has authority to commit its organization. W3C DIDs; two-tier: Declared + Verifiable Credential.
03
Session invitation
Push-based handshake enabling adoption by parties without pre-deployed endpoints — cold-start solved
04
Offer exchange
Signed offers and counteroffers with strict turn-taking. ES256/Ed25519 + RFC 8785 JCS canonicalization.
05
Deal-type terms
Normative schemas for goods_procurement and saas_renewal, with extensible custom_terms for anything else
06
Session state machine
Turn enforcement, sequence ordering, round limits, impasse detection — formally specified transitions
07
Transaction record
Dual-signed, content-addressed record independently generated by both parties. Neither controls the authoritative copy.
08
Audit log
Structured EU AI Act compliance output for every terminal session state — COMPLETED, REJECTED, WITHDRAWN, IMPASSE
Where it stands

Built. Being proposed. Still to come.

A2CN is an open protocol with a complete Python reference implementation, 300+ passing tests, platform adapters, and an A2A extension proposal in review.

Shipped
7
  • Protocol spec v0.2.0 3,700+ lines, 8 components, Apache 2.0
  • Reference implementation Python, 300+ tests passing
  • Session invitation cold-start adoption solved
  • Platform adapters Fairmarkit, Keelvar, Salesforce Revenue Cloud
  • MCP server Claude Desktop, LangChain, LangGraph, Agentforce, Cursor
  • JWT request authentication ES256/Ed25519, anti-replay, DID verification
  • LLM integration pattern Section 13.9, separation of concerns
In progress
1
  • A2A extension proposal OQ-011, submitted — borrows A2A's distribution
Planned
3
  • Neutral third-party record custody optional v0.3 architecture
  • TypeScript reference implementation
  • SDK pip + npm
Maintainer note
Christian
A2CN protocol maintainer
Protocol specification, reference implementation, platform adapters, and MCP server
Focus on cross-organizational authority, sequencing, and tamper-evident records
Open-source implementation under the Apache 2.0 license

A2CN exists because autonomous agents need protocol-level guardrails before they can safely commit to commercial terms across organizational boundaries.

The protocol focuses on the parts that must be shared across parties: signing, DIDs, mandates, dual-signed records, deterministic hashes, and formally specified state machines.

If you are building agent systems that need cross-organizational commitment, feedback on the protocol and reference implementation is welcome.

Get involved

If your platform is about to hit this problem, talk to us.

If you're running a procurement platform, a contract AI, or an agent framework that will soon need to commit on terms across organizational boundaries, we want to hear from you.

Read the spec
3,700+ lines covering eight protocol components, normative JSON schemas, platform integration patterns, and a complete bilateral walkthrough.
spec/a2cn-spec-v0.2.0.md →
Build on it
Python reference implementation with 300+ passing tests. LangChain, CrewAI, and Agentforce compatible. Apache 2.0 license.
github.com/A2CN-protocol/A2CN →
Share implementation feedback
Try A2CN with your platform, open issues for gaps, and help shape the next protocol iteration.
contact@a2cn.io →
Use with an LLM agent
Reference negotiation skills file for LLM-based A2CN agents. Grounded in MIT/Hopkins research on 182K agent-to-agent negotiations. Drop-in for Claude Code, LangChain, CrewAI.
reference-implementation/skills/ →