ACP research corpus
The Agent Client Protocol (ACP) is Zed's open protocol for the client-to-agent seat: an editor, IDE, gateway, or any other host drives a coding agent through a standardized JSON-RPC surface, turning the N x M client/agent integration problem into N + M. This corpus preserves the frozen research input behind the platform's ACP-related decisions and clearly marked later evidence: an industry study of ACP's protocol contract, ecosystem adoption, and product integrations, plus the roadmap analysis that followed it. Where a conclusion here differs from an accepted record in the ADR index or from the current spec position in ACP Conformance, the ADR or the conformance document is authoritative.
Method
The research prompt is preserved so the shared scope, disambiguation rules, and evidence bar behind each product dossier and deep dive remain reproducible.
Product dossiers
The original study covered fifteen products. Later product dossiers are marked as post-synthesis evidence rather than rewritten into the frozen decision-time input. Every dossier examines native implementation vs. adapter, process lifecycle ownership, headless invocation and auth, and channel mapping where relevant.
- Buzz
- Claude Code
- Cline
- Codex CLI
- Cursor
- DeepSeek Harness
- Devin
- Gemini CLI
- Goose
- Grok CLI
- Hermes Agent
- JetBrains
- NetClaw
- OpenClaw
- OpenCode
- Zed
Synthesis
- Synthesis: the ACP protocol contract and ecosystem, the cross-cutting analysis of the wire contract, the v1-vs-v2 breaking-change diff, governance and adoption, and the integration patterns drawn from the dossiers above.
Decision record
- ACP and trogonai: fit and roadmap, the gap analysis and recommended build sequencing that turned the synthesis into a directional plan for hosting external ACP agent CLIs.
Deep dives
Component-level designs that support the decision record's recommended acp-host build:
