How Amplifier's directory-aware context and A2A (Agent-to-Agent — a protocol for autonomous inter-agent communication) combine to create focused, collaborative multi-agent workspaces.
One project. Many agents. Each with the right context — and a way to talk to each other.
February 2026
Amplifier lets you run agents in different subdirectories of the same project — and each one gets its own tailored context. Not a compromise. A feature.
/project/github-localThe self-improvement workspace, annotated:
Each directory pushes down only what's relevant: skills specific to that service,
the right architectural context in AGENTS.md,
and modules tuned for that workload.
In a complex AI workspace, context pollution is real:
github-local agent shouldn't need CXDB internalsamplifier-resolve needs Docker + GitHub, not storage abstractionsAGENTS.md evolves independently per serviceContext pipelines connect everything — via A2A (Agent-to-Agent) communication.
Root holds the high-level plan and project state. Child is delegated a scoped task — parent passes relevant context in the delegation message.
Agents on the same machine, different directories, communicate over A2A. Each maintains its own identity and context — but can query each other.
Result: Deep domain focus AND cross-agent awareness — without compromising either.
In the self-improvement workspace, cross-directory A2A is wired and live:
A2A has a trust system that controls whether messages need human approval or respond autonomously:
Message is queued → session enters INPUT_REQUIRED state → a human must review and respond before the pipeline continues.
Pre-registered agents in known_agents start here by default.
An autonomous child session is spawned immediately → the agent responds without any human in the loop.
Upgrade via a2a trust or direct contacts.json edit.
Once trusted: the github-local-agent responds autonomously. Zero human intervention. Full pipeline automation.
known_agents in bundle.md only accepts {name, url} — no tier parameter supported.
Pre-registered agents always land at "known" tier, requiring a separate manual step to elevate before autonomous communication works.
One-time setup, persistent across all sessions. Best for stable trusted peers.
Programmatic, works across machines, scriptable. Best for CI or dynamic environments.
The ideal future: known_agents in bundle.md should support a tier field — trust levels declared once, versioned with your bundle, applied automatically at startup.
The takeaway: In complex workspaces, Amplifier's directory resolution is the difference between one overloaded agent and a focused team of specialists that still coordinate seamlessly. Scope your context. Connect your agents. Ship faster.