215 tagged local-first, measured the same way as everything else here.
Browse within: knowledge-management 30macos 25Multi-Agent 24artificial-intelligence 15desktop-app 15meeting-notes 15tauri 14knowledge-graph 12obsidian 12angular 11agent-os 9ai-assistant 9awesome-list 9dictation 9
Agent Claude Code
Reviews a single feature's source files for bugs, security issues, performance problems, and code quality concerns. Reports findings by severity. Does NOT make breaking changes — only safe, non-breaking fixes.
Agent Claude Code
Scans a codebase to identify features, modules, and documentation gaps. Maps the project structure and determines which source files belong to which features. Use for bootstrap scanning of undocumented projects.
Agent Claude Code
Creates and updates feature documentation by reading source code and writing real documentation content. Invoke with specific instructions about which doc to create/update and which source files to read.
Agent Claude Code
Anti-false-positive verifier for Murmur. Use AFTER a change is written, to TRY TO BREAK it — run the real gates (cargo test --lib / ng build / ng lint), live-reproduce in a browser against the zoneless Angular app with a mocked Tauri IPC, and hunt for the failure modes this app has actually shipped (sealed-content…
Agent Claude Code
Use as the cross-cutting AI/systems DESIGN authority to decide WHERE a seam goes across the Rust core, Angular FE, and brain — provider/model abstraction, agentic tool-use loop bounds, tool/ACI design, the egress-consent-redaction-ledger firewall, routing, context assembly, a new ingest source or consumption surface.…
Agent Claude Code
Use to diagnose or fix app-wide runtime performance across the Rust->IPC->Angular seam — startup latency, Tauri IPC throughput/heap (event vs Channel, un-windowed transcript payloads), OOM/RAM-pressure guards on DB/transcript/WAV allocations, Angular zoneless change-detection storms, O(n) template method bindings…
Agent
Your general-purpose personal AI assistant.
Agent
Memory keeper — judges episodic staging day by day, promotes durable signal to long-term memory, and stamps dream state. The one brain behind the dream pipeline's remember stage.
Agent
The user's devoted companion and personal keeper, built into Linggen. Helps with anything — herself or by directing the other agents — learns and remembers everything about the one she serves, and quietly keeps their agent-world running. The face on the desktop.
Agent
Use for any Brain OS task delegated to a subagent — reading entity state, checking active decisions, running focus/patterns/retro analysis, or proposing changes that need to honor active decisions. Always uses Brain OS MCP tools (mcpbrain-os) first; falls back to file reads only when the MCP server is unreachable.…
Agent
General-purpose software engineer. Picks up implementation tickets, writes and refactors code, runs tests, and closes with evidence. Good default for any ticket without a more specialized agent. Triggers: any TASK ticket tagged agent=engineer, or when no other agent is a better match.
Agent
Part of strata
Process one parent-directory GROUP of bootstrap candidate files (e.g. .planning/auth-rewrite/PLAN.md + .../CONTEXT.md + .../SPEC.md) as a unit — read all files in the group, decide what concepts deserve their own notes across the set, write each note once, mark every source file processed, return one line per write.…
Agent
Part of strata
Isolated-context memory retrieval. Takes a natural-language query, searches the vault + code graph in this subagent's own context, returns a single curated brief (≤ 600 tokens) to the parent. Use this for heavy synthesis across many notes so the parent's context stays clean; it calls the ranked, supersession-aware…
Agent Claude Code
Implements VZT Flow features observing this repo's boundaries — additive edits, the gotcha list from CLAUDE.md, pull-rebase discipline in a shared worktree, never touching the user's running daily-driver app without relaunching it. Use for routine feature/bugfix work in this repo.
Agent Claude Code
Cuts a VZT Flow release — version bump consistency across all four version fields, tag, watch the release workflow, verify the produced asset list matches what install.sh/install.ps1 expect. Use when asked to cut, ship, or tag a VZT Flow release.
Agent Claude Code
Runs the VZT Flow end-to-end verification ladder (build, tests, TTS-transcribe checks, clean-test latency, paste-test, daemon socket checks, overlay states) and reports real measured numbers — never estimates. Use before claiming a change works, before a release, or when asked to verify VZT Flow.
Agent Claude Code
Design-taste and architecture executor on the delivery board (opus tier). Use for first-impression UI flagships (login, first-run, Studio), contract authoring/splitting at plan checkpoints, cross-workstream tradeoffs, and unblocking tasks lower tiers failed twice.
Agent Claude Code
Standard delivery-board contract executor (sonnet tier). Use for well-specified implementation contracts — layout/CSS work, API endpoints, SSE bindings, test suites, gate scripts written from a spec.
Agent Claude Code
Independent verifier for delivery-board tasks (haiku tier, fresh context). Use to verify a task in VERIFY — re-runs the gate from a clean checkout, audits the diff against the allowlist, and is the ONLY role allowed to move VERIFY → DONE.
Agent Claude Code
Use when a Nimbus PR's CI is red and you need to root-cause the failures instead of push-and-see guessing. Pulls the failed CI job logs via gh, diagnoses against the known CI-only traps (frozen-lockfile drift, cross-platform URL/path flakes, mock.module leaks, gitleaks full-history, the pr-quality fail-fast SIGTERM)…
Agent Claude Code
Use when a PR is failing (or might fail) the Nimbus true-coverage ratchet — the per-file coverage floor enforced by audit:coverage-floor (≥85% line AND ≥80% branch; two separate constants, FLOORPCT / BRANCHFLOORPCT). Drives the file to green: runs the Docker-Linux-authoritative lcov build, reads the exact violations…
Agent Claude Code
Use when the SonarCloud quality gate is failing (or to audit it) on a Nimbus PR — it is the BLOCKING quality gate (CI gates on it). Queries the gate + issues + hotspots via the SonarCloud API, applies fix-not-exclude code fixes for real issues, and for genuine false-positives / safe security hotspots marks them with a…
Agent Claude Code
Adapted from the TORQ Console harness (E:\TORQ-CONSOLE\.claude\agents). These are TorqClaw-local definitions. The Console harness drives a different product through .torq/launch/ watcher scripts and hardcoded E:\TORQ-CONSOLE\... paths; running those agents against this repo would read specs from and write verdicts…
Agent
Part of forkmind
Offloads conversation context into ForkMind's encrypted, immutable DAG capsules so the live model window can be compacted without losing anything. Spawn when context is getting full, when the user says "save this and clear it", "archive the earlier discussion", "offload context", or when a large block (file dumps…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: