AACP
PulseGate's liveness check found it on 3 Oct 2026; it is registered on GitHub and has been in the index since 27 Aug 2026. How this is checked
AACP is an MIT-licensed open protocol and encoder framework that converts natural-language agent instructions into typed coordination packets. It provides deterministic encoders, validated API workflows, community rules, and auditability for developers building multi-agent systems.
Inferred · not functionally tested
Overview
6 featuresPurpose: Making multi-agent instructions deterministic, typed, and auditable across repeated workflows.
Inferred · not functionally tested
Audience: AI developers building multi-agent systems
Inferred · not functionally tested
Functions: agents, workflow_automation
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: MIT · platforms: WEB · deployment: browser, self_hosted, cli, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: aacp.dev · github.com. These links do not verify the individual claims.
AACP sits in PulseGate's Multi-agent & orchestration category. Inferred · not functionally tested: It focuses on making multi-agent instructions deterministic, typed, and auditable across repeated workflows. Inferred · not functionally tested: AACP is an open-source project aimed at AI developers building multi-agent systems. Basis unknown · not verified: AACP is open source under the MIT license. Basis unknown · not verified: AACP is available on the web, the command line, and API, and it can be self-hosted.
Behind AACP is Andrew Mackay, and it first shipped in 2026. The project is developed in the open on GitHub with 13 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are natural language encoding, typed packets, and deterministic outputs. Inferred · not functionally tested: Catalogued interfaces include a public API.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Natural language encoding
- Typed packets
- Deterministic outputs
- Audit trails
- Protocol specification
- API validation
Topics: Inferred · not functionally tested
Built with & integrations
- openai
- bgpt- in the HTML
- multiple
- bLangChain in the HTML
- anthropic
- bclaude in the HTML
- Cloudflare
- cf-ray header
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed27 Aug · 05:11 UTCListing seen at its public sourceSource: Store homepage redirect (Phase B backfill) · Open
Frequently asked questions about AACP
- What is AACP?
- Inferred · not functionally tested: AACP focuses on making multi-agent instructions deterministic, typed, and auditable across repeated workflows. It is catalogued under Multi-agent & orchestration on PulseGate.
- Who is AACP for?
- Inferred · not functionally tested: AACP is an open-source project built for AI developers building multi-agent systems.
- Is AACP free?
- Basis unknown · not verified: Yes — AACP is open source under the MIT license and free to use.
- What platforms does AACP run on?
- Basis unknown · not verified: AACP runs on the web, the command line, and API. It can also be self-hosted.
- Is AACP still active?
- PulseGate's liveness check found it on 3 Oct 2026. Its GitHub repository shows 13 commits in the last 90 days.
- What projects are similar to AACP?
- Similar projects tracked by PulseGate include AAP, Agent Client Protocol, and isaac-acp.AAPAgent Client Protocolisaac-acp
- Who develops AACP?
- AACP is developed by Andrew Mackay.
- When did AACP launch?
- AACP first shipped in 2026.
Similar projects
Closest matches by what these projects do