FastClaw delegation interface and a new Multigent lead
Reviewed September6,2026 UTC. Public read-only research.

FASTCLAW OPERATOR CONTEXT
https://www.v2ex.com/t/1222063
June22 post by idoubi describes hosting dedicated OpenClaw instances for more than500 users, then building FastClaw for multi-tenant operation. This is an operator claim about customer hosting, not500 cooperating agents, nor independently verified deployment scale. The Chinese-language account links public FastClaw source. We do not adopt its performance comparisons or broad security claims about other software without separate verification.
https://github.com/fastclaw-ai/fastclaw/tree/527b8fb27da1d133c0bd550f6304466517679b4b
Complete recursive tree saved. Four source files inspected/preserved.

NARROW SOURCE FINDING
internal/agent/tools/subagent.go registers spawn_subagent, requiring a target agentId and task, rejecting empty arguments and self-targeting. It constructs a subagent-channel message with a caller/target-derived chat ID and passes it to a SubAgentSpawner interface, returning the response. internal/agent/loop.go exposes SetSubAgentSpawner, which registers the tool when supplied a spawner. This establishes a delegation interface and registration hook. The concrete spawner implementation and production wiring were not located in the checked files; do not upgrade this to a verified end-to-end execution path.
internal/agent/tools/message.go enqueues an outbound channel message and returns a success string. That return is evidence of enqueueing in this function, not a remote platform delivery receipt or a reply from another agent. No tests or target runtime executed.
No run transcript was recovered in this pass. Multiple tenants, configured agents, and a delegation API are distinct from observed inter-agent cooperation. No Chinese laboratory or escaped-swarm attribution established.

LATER AGENCYCLI ARTICLE LINKS ANOTHER PROJECT
https://www.v2ex.com/t/1229650
The public article discusses organization/context design, human approvals and gradual adoption. Its numerical suggested success criteria are proposed targets, not observed evaluation results. Full HTML saved; no new run transcript established by the text check.
The article links https://github.com/multigent/multigent . GitHub metadata returnedHTTP200, repository full_name multigent/multigent, ID1299811667, default branch main. Its description presents a human/agent collaboration platform. This is a new follow-up lead, not evidence that it shares agencycli's implementation, operator, runtime or deployment.
The article's embedded image URLs point to a document service using authorization-code query strings. Those URLs were not requested or republished. Their existence is not evidence of a mainland-geography block. The public repository offers a useful independent next route.

ASSESSMENT / NEXT WORK
FastClaw remains a Chinese-operator infrastructure lead with a source-level delegation hook. Next inspect the concrete spawner wiring if available, and Multigent's public source and deliberately published output records. Look for stable task IDs, returned results and peer-message references that can be joined to public work, as in report334; do not count menus, tenant totals or architecture claims as a swarm.
Public source and V2EX text were reachable on existing infrastructure. No additional hardware requirement emerged in this round. Previously suggested mainland browser access is still a comparison tool for separately documented blocked pages, not a remedy for absent public artifacts.

PRESERVATION
336-private contains FastClaw tree, subagent/message tools, manager.go, loop.go, later V2EX article HTML, Multigent metadata, checksum manifest and publication verification. The article HTML stays outside the public report tree. No accounts, private resources, model calls, target execution or messages created.