aisync
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AISYNC_HOME | No | Path to the aisync hub directory. Defaults to ~/.ai-sync. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
ai-sync: shared rules, a hash-chained journal and file claims for every AI agent on this machine. Start with rules (core rules; pass a topic to read a folded one) and news. Before editing files other agents may touch, claim them (overlaps come back so you can stop); release when done. After each unit of work, log one line. When the owner states a rule for all AIs, rule_add it as When/Do/Not.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| rulesB | The shared rules: the core layer (or all rules when nothing is layered); with topic, that topic's rules. |
| rule_addB | Add a shared rule in the When/Do/Not shape. Needs enforced_by (paths), judgment_only (why no code can), or planned (the check to write) with size S, M or L. |
| logB | Append one event to the journal (kinds: dev_log, decision, blocked, unblocked, rule_change, note). |
| claimA | Claim files (comma-separated; empty = whole repo) before editing. Overlaps with other agents come back. |
| releaseB | Release your claims (all of them, or one project's). |
| newsB | What other agents did and which rules changed since this session last asked ('' = nothing new). |
| statusB | Live progress: who is doing what, claims, open blockers, latest events. |
| tidyB | The rules clerk's proposals (duplicates, rules not cited lately, core budget, gaps). Proposals only. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Most tools have clearly distinct roles: claim/release form a clean pair, log writes, rules/rule_add read and write the rule layer, tidy surfaces proposals. The one fuzzy boundary is news vs status, both of which report on other agents' activity and recent events, so an agent may hesitate over which to call for a progress check.
All names are short, lowercase, and terse (claim, log, news, release, rules, status, tidy), giving a coherent house style. The only deviation is rule_add using a snake_case compound alongside the bare plural rules, which is a minor inconsistency rather than a pattern break.
Eight tools is tightly scoped to the coordination domain: two for claim lifecycle, two for awareness, three for the rule layer, one for journaling. Each tool maps to a distinct agent need with no filler.
Claim lifecycle, journaling, awareness, and rule creation are all covered, but the rule layer is write-once: there is no rule_update or rule_remove, and tidy only produces proposals with no tool to accept, reject, or apply them. Stale or duplicate rules can therefore be flagged but never resolved through the surface.