GitHub verdict · build Solution request

ACP stdio JSON-RPC adapter for agy agent CLI

Built for AI agent orchestrators integrating coding agents.

“## Summary Please add an `--acp` (or equivalent) flag that runs `agy` as a JSON-RPC-over-stdio agent server, matching the [ACP](https://github.com/zed-industri…”

The receipts — real demand

“## Summary Please add an `--acp` (or equivalent) flag that runs `agy` as a JSON-RPC-over-stdio agent server, matching the [ACP](https://github.com/zed-industries/agent-client-protocol) shape that `gemini-cli --acp`, `claude --acp`, `cursor-agent acp`, `codex acp`, etc. already implement. ## Background `agy` v1.0.0 currently exposes only: | Mode | Streaming output | Tool approval | Cancel | Conversation state | |-…”
GitHub · view original →

Full dossier

Unlock the full dossier — free

Every corroborating quote, the source receipts, and the community echo. One email, no payment.

6.1 / 10 · demand score
Pain 7
Willingness to pay 0
Feasibility 7
Specificity 9
Audience 6
Competition 7

Why this is a gap

Surfaced from a high-intensity complaint with clear willingness to pay and a specific, reachable audience.

The market

AI agent orchestrators and developers building multi-agent systems need standardized stdio JSON-RPC interfaces to plug coding agents into larger frameworks. No search volume data, but six named competitors indicate active adoption within the AI engineering community.

Competition & the opening

Wedge play crowded — win on a narrow angle Moat 3/10 · thin angle Market 3/10 · small niche
Crowded market · 7/10 vs Model Context Protocol (MCP) — Anthropic's open stdio JSON-RPC 2.0 standard for agent tool adaptersLangChain / LangGraph CLI tooling — Python-native agent orchestration with stdio/subprocess transportAutoGen (Microsoft) — multi-agent framework with CLI-accessible agent interfacesSemantic Kernel — Microsoft SDK with agent process/stdio integration patternsCrewAI — agent orchestration framework with CLI entry points and IPC patternssmol-ai / smol-developer — minimal agent CLI wrappers with JSON-based communication

Model Context Protocol (Anthropic's standard), LangChain/LangGraph, AutoGen, Semantic Kernel, CrewAI, and smol-ai all provide stdio or subprocess agent communication. The gap is likely in ease-of-adoption for non-Python stacks (agy appears to be a different language/runtime) or simpler, lighter-weight stdio adapters that don't require heavy framework dependencies.

What's hard to build

Ensuring strict ACP spec compliance while maintaining backward compatibility with the existing agy CLI is non-trivial. Testing across multiple agent orchestrators (Anthropic, LangChain, Microsoft, etc.) to verify interop requires access to live instances of each platform. Performance under high message throughput (many simultaneous tool calls) needs benchmarking.

Why now

ACP/MCP stdio standards are consolidating as the interop layer for agent orchestration; CLI-native agent tooling is fragmenting and needs a universal adapter.

How you'd monetize

freemium open-source with optional hosted orchestration layer ($49–199/mo) or pe