Connection check
verified live · 20h ago
liminality
Breaks a hard question or decision into grounded sub-questions and returns a checkable route.
Tools
22
GitHub stars
—
Installs / wk
—
Licence
—
Transport
streamable-http
Last checked
20h ago
Tools & capabilities
22 toolsRead from the running server on 20h ago.
apply_form
fills*question*
Apply form answers to sharpen a task. Apply form answers to sharpen a task.
apply_grade
notechoice*result_id*
Apply a grade-form answer to a result. Apply a grade-form answer to a result.
ask_form
question*max_depthverify_divergence
Create a short form for missing user-specific facts. Create a short form for missing user-specific facts.
catalog
actionentity_aentity_bobjective
Read the capability catalog: action='search' returns every saved candidate for an objective with distinctiveness deltas; action='delta' compares a named entity pair. Read the capability catalog: action='search' returns every saved candidate for an objective with distinctiveness deltas; action='delta' compares a named entity pair.
composio_connect
toolkit*user_id
Create a caller-scoped connection link for a toolkit. Create a caller-scoped connection link for a toolkit.
compress_context
task*text*retention
Compress long context into a task-focused brief. Compress long context into a task-focused brief.
delegation
roletaskaction*outcomehandoff_idunresolved
+7
Create, resume, or report a bounded subagent packet (action='create'|'resume'|'report'). Create, resume, or report a bounded subagent packet (action='create'|'resume'|'report').
export_result
result_id*
Export a caller-owned result in a supported format. Export a caller-owned result in a supported format.
get_capabilities
List solve modes and every public capability. List solve modes and every public capability.
get_result_detail
result_id*
Fetch the full caller-owned result behind a lean solve. Fetch the full caller-owned result behind a lean solve.
get_settings
user_id
Read this caller's saved solve and safety settings. Read this caller's saved solve and safety settings.
handoff
taskaction*detailsubjectevidenceresources
+7
Create, safely resume, or list caller-scoped cross-session checkpoints (action='create'|'resume'|'list'). Create accepts an optional subject and source_sessions; Liminality assigns… Create, safely resume, or list caller-scoped cross-session checkpoints (action='create'|'resume'|'list'). Create accepts an optional subject and source_sessions; Liminality assigns the subject number. Resume by handoff_id — 'latest' picks the newest unfinished resumable checkpoint; detail='full' returns the complete checkpoint.
manage
action*payload
Compatibility router for retained-context lifecycle actions. Compatibility router for retained-context lifecycle actions.
optimize
top_kbudgettarget*objective*
Rank bounded one-factor variants for a route against your stated objective; candidates remain unsaved. Rank bounded one-factor variants for a route against your stated objective; candidates remain unsaved.
register_asset
kindname*user_idattributes
Register a caller-owned resource for future grounding. Register a caller-owned resource for future grounding.
report_feedback
toolratingcommenthelpfulmissinguser_id
+1
Report structured feedback on a result. Report structured feedback on a result.
report_outcome
leafnoteintentworkedendpointread_back
+7
Report verified real-world outcome evidence for a result. Report verified real-world outcome evidence for a result.
research
question*max_depth
Run a multi-source research pass for a question. Run a multi-source research pass for a question.
set_priorities
items*user_id
Save caller-scoped tasks and importance signals. Save caller-scoped tasks and importance signals.
set_settings
user_idsettings
Save caller-scoped settings from one dict (depth, optimization, trace, relay, governance); keys and values in get_capabilities. Save caller-scoped settings from one dict (depth, optimization, trace, relay, governance); keys and values in get_capabilities.
solve
depthtracecontextuser_idverbosequestion*
+5
Decompose, ground, and answer a non-trivial task. Supports saved or per-call depth, safe trace, caller tools, and lean/full output. Decompose, ground, and answer a non-trivial task. Supports saved or per-call depth, safe trace, caller tools, and lean/full output.
taxis
user_id