KruschStack
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@KruschStack remember we never use eval() in payment modules"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
KruschStack (krusch-stack)
krusch-stack (v1.3.0) is a local, zero-cloud control plane for AI coding agents (Claude Code, Cursor, Windsurf, Antigravity, Codex). It gives your agent persistent cross-session memory, Turn-0 workspace grounding, spin-loop protection, and two-phase commit (2PC) file safety backed by Node 22 native node:sqlite.
⚡ 30-Second Value Demo & Progressive Quickstart (Zero API Keys, Zero Docker)
Run the offline 3-act walkthrough in <1s inside an isolated temporary SQLite workspace before touching any project files:
npx krusch-stack demoKruschStack v1.3.0 -- 3-Act Zero-Cloud Control Plane Walkthrough (<1s, node:sqlite WAL)
[Act 1] Cross-Session Memory
Session 1 saved invariant #1 ("Never use eval() in payment modules" @ src/pay.js)
Session 2 cold-restarted -> hydrated invariant #1 (SHA-256 drift_status: VALID)
[Act 2] Unsafe Edit, Spin-Loop & Output Defect Refusal
1. Proposed eval(payload) edit -> BLOCKED_INVARIANT (0 bytes written to disk)
2. Repeated failing tool call -> BLOCK_SPIN_LOOP (0 duplicate executions)
3. Emitted raw np.float64(0.015) -> REJECT_OUTPUT_DEFECT (caught before user reply)
[Act 3] Verified 2PC Atomic Apply
Staged unified diff -> write-ahead journal -> POSIX atomic rename -> APPLIED (src/pay.js)
Result: PASS (3/3 acts verified offline in 48ms)Install Into Your Workspace
# 1. Configure Claude Code, Cursor, Windsurf & Antigravity (defaults to lean 19-tool coding-agent profile)
npx krusch-stack init
# 2. Verify Node >= 22, SQLite WAL health, and all 21 control-plane tables
npx krusch-stack doctor
# 3. Inspect any recent block, memoized read, or 2PC commit ("Why did the agent block that?")
npx krusch-stack explainPrefer letting your coding agent set it up for you? Paste this prompt into Claude Code, Codex, Cursor, Windsurf, or Antigravity:
Read https://raw.githubusercontent.com/kruschdev/krusch-stack/main/INSTALL.md and set up krusch-stack on this machine.Opinionated Profiles (Pick Only What You Need)
Profile Flag | Tools Exposed | Approx. Schema Budget | Best For & Included Capabilities |
| 5 tools |
| Persistent Memory Only: Decisions, invariants, pre-commit |
| 19 tools (Default for |
| Daily Coding Agents: Persistent memory + AST symbol/call-graph search ( |
| 27 tools |
| Backend & Systems Engineering: Adds bounded OS PageMemory ( |
| 39 tools (Default for |
| Full Ecosystem: Adds Frontend Design templates and Workspace Docs RAG ( |
Need custom composition or Docker? Use npx krusch-stack mcp --components context,git,harness, npx krusch-stack init --modular (dedicated per-pillar MCP entries), or docker compose up -d (http://127.0.0.1:3780/health + companion PostgreSQL 16 db/init.sql).
📘 Focused 3-Minute Guides & Community:
Adding Reliable Memory to Cursor and Claude Code in One Command (
--profile memory-only, 5 verbs, SHA-256 span drift vs. staleCLAUDE.md)Why Two-Phase Commit (2PC) for Agent File Writes (staging unified diffs, pre-commit invariants, and
<32msSIGKILL-safe journal recovery)GitHub Discussions (questions, local GPU setups, and benchmark reproductions)
🎬 Optional Watch: 100-Second Narrated Product Tour (1080p)

▶️ Stream 1080p HD Product Tour (
01:40, with audio) | Interactive Player onkrusch.dev| Local MP4 | WebM | Closed Captions (.srt)
Related MCP server: threadline-core
🩹 Before vs. After: Three Agent Failure Modes Fixed
1. Agent Amnesia & Stale Rules
Before (
CLAUDE.md/ Stateless Chat): Your agent forgets last week's architectural constraint in a new session, or blindly follows an outdated rule inCLAUDE.mdlong after the underlying function moved or was refactored.After (
krusch-context-mcp):krusch_context_retrievehydrates token-budgeted decisions and invariants at Turn 1, verifies anchored code spans via SHA-256 (VALID,HEALED_LINE_SHIFT, orSTALE_DRIFT), and tracks explicit supersession lineage viakrusch_context_revise.
2. Unsafe Direct File Writes & Torn Multi-File Edits
Before (Unchecked
write_file): Your agent overwrites 4 files directly on disk, introduces a banned pattern or breaks imports, and leaves a half-written repository if the process crashes or hits a timeout mid-edit.After (
krusch-harness2PC):krusch_runaudits proposed edits against active invariants (krusch_context_nudge) before touching disk and stages a unified diff in SQLite.krusch_apply_diffcommits changes through a<32mswrite-ahead journal (harness_apply_journal) and POSIX atomic rename with automaticSIGKILLstartup rollback.
3. Tool Spam, Spin Loops & CSV "NA" Traps
Before (Raw Tool Loop): A local or cloud model burns 15 turns re-reading the same file with identical arguments, misparses literal
"NA"(North America) in a CSV asNaN, or leaksnp.float64(0.015)/ unresolved placeholders into its final answer.After (
grounded-harness): Injects zero-LLM Turn-0 workspace schema hazards (keep_default_na=False, JSONnull/[]wildcards, SQLite DDL), memoizes repeat reads (MEMOIZED_PRIOR_READ), blocks spin loops in0re-executions (BLOCK_SPIN_LOOP), and gates objective output defects (REJECT_OUTPUT_DEFECT) while costing0extra turns when clean.
🧩 Adopt One Piece Without the Rest (Zero Ecosystem Lock-In)
You do not have to buy into all 10 pillars to use krusch-stack. Every subsystem ships as an independent MIT repository and as an isolated ESM subpath export:
Capability Needed | Standalone Repository | Single-Piece CLI or ESM Import via |
Persistent Memory Only ( |
| |
Turn-0 Grounding & Spin-Loop Gate |
| |
2PC File & Tool-Action Harness |
| |
Reusable Runtime Bricks (Node/TS & Python) |
|
🏗️ Architecture: Deterministic Control Plane vs. Interchangeable LLM
krusch-stack keeps state, safety invariants, schema hazards, and atomic file commits inside a deterministic local database (node:sqlite WAL by default, with 21-table PostgreSQL 16 + pgvector DDL parity in db/init.sql), so you can swap local open-weights models and frontier cloud APIs without losing memory or safety guarantees:
IDE / Agent Host (Claude Code, Cursor, Windsurf, Antigravity, Codex, HTTP Client)
│
▼
┌───────────────────────────────────────────────────────────────────────────────────┐
│ DETERMINISTIC LOCAL CONTROL PLANE (SQLite WAL / PostgreSQL 16 DDL) │
│ │
│ ┌─────────────────────────┐ ┌─────────────────────────┐ ┌───────────────────┐ │
│ │ 1. Working Memory │ │ 2. AST & Graph Context │ │ 3. Grounded Gate │ │
│ │ • Invariants & lineage │ │ • Symbol & call graphs │ │ • Turn-0 schemas │ │
│ │ • SHA-256 span drift │ │ • Bounded OS PageMemory │ │ • Spin-loop block │ │
│ │ • git blame co-change │ │ • Temporal ADR graph │ │ • Defect-only gate│ │
│ └─────────────────────────┘ └─────────────────────────┘ └───────────────────┘ │
│ ┌─────────────────────────────────────────┐ ┌────────────────────────────────┐ │
│ │ 4. Two-Phase Commit (2PC) Harness │ │ 5. Observability & Routing │ │
│ │ • Pre-disk invariant nudge │ │ • `explain` & `GET /telemetry` │ │
│ │ • <32ms write-ahead journal + rename │ │ • <25µs L1-L3 Cascade Router │ │
│ └─────────────────────────────────────────┘ └────────────────────────────────┘ │
└────────────────────────────────────────┬──────────────────────────────────────────┘
│ Bounded prompts + verified tool calls
▼
┌───────────────────────────────────────────────────────────────────────────────────┐
│ INTERCHANGEABLE LLM WORKER │
│ Local 12-48 GB Ollama (`$0.00`: Gemma 4 31B, Qwen3-Coder 30B MoE, 7B/8B) │
│ or Frontier Cloud API (Gemini 4 Argon, Claude, GPT, DeepSeek, OpenRouter) │
└───────────────────────────────────────────────────────────────────────────────────┘Complete 10-Pillar Reference Table
Capability (Internal Module Name) | Standalone Repo | Key Tools & Subpath Surfaces | Default Storage |
Persistent Working Memory & Git Alignment ( |
|
| |
Codebase AST & Call-Graph Search ( |
|
| |
Bounded OS Page Memory ( |
|
| |
Temporal Graph Context ( |
|
| |
Signed Module Reuse & 2-Hop Blast Radius ( |
|
| |
2PC Staged File & Action Harness ( |
|
| |
Turn-0 Schema Grounding & Spin-Loop Gate ( |
|
| |
Frontend Design & Component Templates ( |
|
| |
Workspace & Docs RAG ( |
|
| |
Task Routing, Prerequisite ToolGraph & Polyglot Audit ( |
| In-Memory ( |
🖥️ Recommended Local Open-Weights Setups ($0 API Spend, 12-48 GB VRAM)
Copy-pasteable local configurations tested against krusch-stack scale profiles (SMALL_MODEL and MID_MODEL):
Hardware Tier | Recommended Local Models & Adapters | Ollama / Runtime Settings | Recommended |
12-16 GB VRAM (RTX 3060 / 4060 Ti / 4070) |
|
|
|
24 GB VRAM (RTX 3090 / 4090) |
|
|
|
32-48 GB VRAM (RTX 5090 / A6000 / Apple Silicon) |
|
|
|
Where the Control Plane Closes the Gap (and Where Frontier Models Still Lead)
Benchmark / Workload | Raw Model Baseline | With | Relative Lift / Cost Savings |
Aider Polyglot ( |
|
|
|
BIRD-SQL ( |
|
|
|
Adyen DABstep ( |
|
|
|
UC Berkeley BFCL v3 Live ( |
|
|
|
DolphinBench Tool Hygiene ( |
|
|
|
Honest Frontier Boundary: Deterministic memory, Turn-0 schema grounding, and 2PC verification multiply open-weights reliability (
40%-57%at$0.00, beating several ungrounded commercial cloud stacks), while frontier reasoning models (Gemini 4 Argon,GPT 5.6 Luna) still hold the75%-91%ceiling on deep multi-hop synthesis and long-horizon recovery when paired with the exact samekrusch-stackcontrol plane.
📊 External Benchmarks (3-Tier Verification Taxonomy & One-Command Reproduction)
Evaluated across 335,000+ traces and 14 external benchmarks (95/95 SHA-256 verification gates). To keep claims auditable, every benchmark result is separated into three explicit verification tiers:
Tier 1 -- Maintainer-Reviewed & Merged Upstream:
RouteWorks/RouterArenaPR #169 merged intomain @ 844e93b(0.7263github-actions[bot]CI-verified across8,400/8,400live receipts at$0.3802/1K; leaderboard table row queued for next batch refresh).Tier 2 -- Uploaded & Queued on Public Leaderboard: Official
DolphinBench(600/600tasks) archives uploaded todolphinbench.ai(status: "queued"awaiting maintainer leaderboard refresh):91.17%(547/600@$24.54)Gemini 4 Argon Low + SovereignMemoryStore(UUID c047b063) and54.17%(325/600@$0.00) stockGemma 4 31B(UUID 288671ad).Tier 3 -- Self-Run Clean-Room with SHA-256 Audit Logs: Reproducible harness evaluations published with raw JSON receipts in
BENCHMARKS.mdandkrush420/sovereign-g4-benchmarks.
Stack Pillar | External Benchmark | Headline Result | Verification Tier |
Cascade Router | RouteWorks RouterArena ( |
| Tier 1: Merged upstream (PR #169) |
Memory + Control Plane | Official DolphinBench ( |
| Tier 2 ( |
Working Memory ( | Official Snap LoCoMo ( |
| Tier 3: Self-Run Clean-Room (SHA-256 logs) |
Long-Horizon Memory | ICLR 2026 BEAM ( |
| Tier 3: Self-Run Clean-Room (SHA-256 logs) |
Security & Policy Floor | ETH SpyLab AgentDojo v1.2.2 ( |
| Tier 3: Self-Run Clean-Room (SHA-256 logs) |
Code AST & Call Graph | ACL 2025 CoIR ( |
| Tier 3: Self-Run Clean-Room (SHA-256 logs) |
2PC & Grounded Harnesses | Aider Polyglot ( | Polyglot | Tier 3: Self-Run Clean-Room (SHA-256 logs) |
Deferred MCP ( | UC Berkeley BFCL v3 Live ( |
| Tier 3: Self-Run Clean-Room (SHA-256 logs) |
One-Command Clean-Room Verification (<5s, Zero API Keys)
Clone the repository and verify the deterministic control-plane invariants, 2PC SIGKILL crash rollback, spin-loop/defect gates, and SHA-256 benchmark receipts locally:
git clone https://github.com/kruschdev/krusch-stack.git
cd krusch-stack
npm ci
npm run bench:reproRead the full methodology, competitor tables (Mem0, past.dev, Honcho, NotDiamond, Martian), and whitepapers in BENCHMARKS.md, Paper #27: Return on Memory (PDF), Paper #26: What DolphinBench Taught Me About Local AI, and Paper #30: Ontological Brick Exchange.
🔍 Production Signals, Observability & Failure Recovery
krusch-stack is built to fail closed and answer "Why did the agent do that?" without external SaaS tracing:
Instant Decision Explanations: Run
npx krusch-stack explain [task_or_session_id] [--limit 10] [--json]to inspect the exact rule ID, invariant match, spin-loop hash, or unified diff behind any allowed, memoized, held, or blocked agent step.Structured Telemetry Endpoint: Query
GET /telemetryonnpx krusch-stack serve(127.0.0.1:3780, guarded byHost/OriginCSRF checks and constant-time SHA-256KRUSCH_STACK_API_TOKENBearer auth) for live counters (blocked_invariant,spin_loops_blocked,memoized_reads,output_defects_caught,stale_drift,journals_rolled_back).2-Process
SIGKILLCrash Drill: Runnpx krusch-stack doctor --crash-drillto verify thatharness_apply_journal+ startuprecoverInFlight()cleanly roll back interrupted multi-file renames after hard process termination.Fail-Closed SQLite Corruption Quarantine:
PRAGMA quick_checkdetects corrupted B-trees or FTS5 shadow tables and surfacesepistemic_status: "STORAGE_ERROR"instead of silently returning empty memories.
See docs/PRODUCTION.md for Solo node:sqlite WAL vs. Multi-User Team PostgreSQL 16 deployment patterns, security perimeters, and failure recovery playbooks.
🧪 Programmatic Node.js & HTTP Gateway Quick Reference
import { createKruschStack } from 'krusch-stack';
const stack = createKruschStack({ ephemeral: true });
// 1. Cross-session working memory & pre-commit invariant steering (Tier 1)
stack.context.remember({ category: 'invariant', content: 'Never use eval() in production modules.' });
// 2. Turn-0 workspace schema grounding, memoization & defect-only stop gate (Tier 3B)
const grounded = stack.groundedHarness.groundAndStartSession({
session_id: 'gh-001',
goal: 'Compute North America merchant settlement fee rate',
model: 'gemini-4-argon'
});
const stopGate = stack.groundedHarness.verifyStop({
session_id: 'gh-001',
candidate_answer: '0.015',
expect_non_empty_answer: true
});
// 3. Staged 2PC file execution & decision observability (Tier 3A + Observability)
const staged = stack.harness.run({
goal: 'Add greeting helper',
edits: [{ file_path: 'src/greet.js', content: 'export const greet = (n) => `Hello ${n}`;\n' }]
});
const metrics = stack.observability.getMetrics();
const auditTrail = stack.observability.explainDecisions({ limit: 5 });HTTP Gateway (npx krusch-stack serve, default http://127.0.0.1:3780): Exposes GET /health, GET /telemetry, GET /tools, POST /call, POST /action-harness/*, POST /grounded-harness/*, POST /hydrascope/*, POST /brick-exchange/*, POST /tool-graph/*, POST /polyglot-audit/*, and POST /resilience/* while keeping ALL_STACK_TOOLS.length === 39 strictly stable.
🤗 Open-Weights Models & Datasets Trained Through krusch-stack
Resource | Hugging Face / GitHub | Role & Base Architecture |
31B Dense SRE LoRA ( |
| |
30B MoE Coding LoRA ( |
| |
8B Edge Referee LoRA ( |
| |
120B Teacher QLoRA ( |
| |
SFT + DPO Dataset ( | 7 zero-leak splits of test-gated remediations, AST code audits, and tool-calling DPO pairs | |
Hermetic Benchmarks ( | Raw JSON evaluation logs, SHA-256 manifests, and merged | |
Jean SRE Daemon ( | Autonomous 24/7 11-phase code auditor and test-gated remediation harness |
🤝 Contributing & License
Contributions, bug reports, and clean-room benchmark reproductions are welcome! Read CONTRIBUTING.md for local node --test workflows, isolated single-engine development (src/engines/*), and CI invariants (INV-STACK-01..15), and docs/PRODUCTION.md for production operations.
MIT © kruschdev kruschdev@users.noreply.github.com
Available Tools
39 toolscss_to_tailwindCRead-onlyIdempotent
Convert raw CSS declarations into deterministic Tailwind utility classes.
Inputs: css (required).
generate_color_paletteBRead-onlyIdempotent
Generate a 5-stop HSL color palette with WCAG 2.1 contrast ratios against dark and light surfaces.
Inputs: harmony, base_hex.
generate_responsive_breakpointsBRead-onlyIdempotent
Generate 375px (mobile), 768px (tablet), and 1440px (desktop) responsive layout specs.
Inputs: component_type.
get_agent_steeringBRead-onlyIdempotent
Read the workspace agent.md steering directives.
Inputs: no named parameters.
get_canonical_templateCRead-onlyIdempotent
Retrieve a canonical HTML/SVG, Vercel, or @krusch/toolkit & krusch_toolkit Lego starter template (article-shell, site-header, footer-deadbolt, cyber-grid, deadbolt-svg, nav-back, lego-node-api, lego-mcp-server, lego-sse-route, lego-react-shell, lego-fastapi-app, lego-cloudflare-worker, lego-webhook-route, lego-vercel-nextjs-shell, lego-vercel-edge-sse, lego-vercel-json).
Inputs: template_id (required).
get_workspace_statusARead-onlyIdempotent
Inspect document counts and MIME breakdown in the workspace hub.
Inputs: no named parameters.
krusch_abortBDestructiveIdempotent
Cancel and abort an in-progress or staged task.
Inputs: task_id (required).
krusch_apply_diffBIdempotent
Apply a STAGED task diff to disk after passing the invariant gate.
Inputs: task_id (required).
krusch_context_healthBRead-onlyIdempotent
Inspect memory store statistics and INV-12 span-grounded drift counts.
Inputs: no named parameters.
krusch_context_nudgeARead-onlyIdempotent
Audit staged code or unified diffs against active project invariants (max 3 findings).
Inputs: code, trigger, file_path, enable_lego_guard.
krusch_context_rememberB
Persist a durable rule, architectural decision, bug root-cause, lesson, or blocker with optional file/span provenance.
Inputs: content (required), category (required), provenance.
krusch_context_retrieveCRead-onlyIdempotent
Hydrate active project invariants, decisions, bugs, lessons, and span-grounded drift status.
Inputs: query, category, condense, limit_tokens, +3 more.
krusch_context_reviseCIdempotent
Supersede an evolving decision with lineage or invalidate an obsolete rule.
Inputs: action (required), target_id (required), reason, provenance, +1 more.
krusch_diffARead-onlyIdempotent
Retrieve the staged unified diff for a task before applying to disk.
Inputs: task_id (required).
krusch_explainARead-onlyIdempotent
Explain why a task was staged or blocked by project invariants.
Inputs: task_id (required).
krusch_fs_locateCRead-onlyIdempotent
Fast file metadata and glob lookup without reading full file contents.
Inputs: pattern, category, min_size_bytes.
krusch_fs_page_treeARead-onlyIdempotent
Inspect the structural table of contents (page numbers, section titles, line ranges, SHA-256 hashes) before reading a file.
Inputs: path (required).
krusch_fs_read_pageBRead-onlyIdempotent
Read a specific page of a file along with anchored notes and SHA-256 drift verification (VALID vs STALE_DRIFT).
Inputs: path (required), page_number.
krusch_fs_remember_on_pageC
Pin a durable operational note or warning to an exact file page anchored by SHA-256 hash.
Inputs: note (required), path (required), category, page_number.
krusch_fs_searchCRead-onlyIdempotent
Search structural file pages and anchored PageMemory notes.
Inputs: query (required), limit, category, limit_tokens.
krusch_fs_syncBIdempotent
Index or refresh workspace files into the structural page store.
Inputs: paths.
krusch_git_dependency_graphBRead-onlyIdempotent
Trace inbound callers and outbound callees for a symbol before modifying signatures.
Inputs: symbol (required), repo.
krusch_git_file_symbolsBRead-onlyIdempotent
List all extracted AST symbols and line spans within a specific file.
Inputs: file_path (required), repo.
krusch_git_list_reposARead-onlyIdempotent
List indexed repositories and symbol statistics in the workspace.
Inputs: no named parameters.
krusch_git_read_blobCRead-onlyIdempotent
Read bounded lines from a file in the repository.
Inputs: path (required), repo, end_line, start_line.
krusch_git_read_treeBRead-onlyIdempotent
List files and directories at a given path inside the repository.
Inputs: path, repo.
krusch_git_search_symbolsCRead-onlyIdempotent
Locate functions, classes, methods, exports, and markdown sections across the codebase.
Inputs: query (required), repo, symbol_type.
krusch_git_semantic_searchCRead-onlyIdempotent
Search symbols and code snippets using keyword + structural token ranking.
Inputs: query (required), repo, limit, limit_tokens.
krusch_rejectBIdempotent
Reject a staged diff with a recorded reason without writing to disk.
Inputs: task_id (required), reason.
krusch_route_taskCRead-onlyIdempotent
Classify a coding or reasoning prompt in <25µs into L1_FAST_LOCAL, L2_SWE_MOE, L2_5_BURST_120B, or L3_FRONTIER_REFEREE.
Inputs: prompt (required), task_type, budget_tier.
krusch_runB
Stage proposed file edits as a unified diff and run the pre-commit invariant gate without mutating the working tree.
Inputs: goal (required), edits.
krusch_stack_statusBRead-onlyIdempotent
Return aggregate readiness and telemetry across all KruschStack engines.
Inputs: no named parameters.
krusch_task_statusARead-onlyIdempotent
Inspect the state of a staged 2PC task (STAGED, BLOCKED_INVARIANT, APPLIED, REJECTED, ABORTED).
Inputs: task_id (required).
list_canonical_templatesARead-onlyIdempotent
List all available canonical HTML/SVG component templates and @krusch/toolkit & krusch_toolkit Lego starter bricks.
Inputs: no named parameters.
list_drive_workspaceBRead-onlyIdempotent
List all files stored in the workspace hub.
Inputs: folder.
query_design_rulesBRead-onlyIdempotent
Retrieve typography, contrast, spacing, and layout rules from the design system store.
Inputs: query, category.
read_drive_fileBRead-onlyIdempotent
Read a document from the workspace store by path with MIME disambiguation.
Inputs: path (required).
search_drive_ragCRead-onlyIdempotent
Search workspace documents, Docs, Sheets, and Slides.
Inputs: query (required), limit.
write_drive_fileCIdempotent
Write a Markdown, Google Doc (.gdoc), Sheet (.gsheet), or Slide deck (.slides) to the workspace with INV-14 MIME disambiguation.
Inputs: path (required), content (required), mime_type.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 39 tools
Tools are grouped by engine prefix, but there are several overlapping search/read families: krusch_git_semantic_search vs krusch_git_search_symbols vs krusch_fs_search, and three different file-read tools (krusch_git_read_blob, krusch_fs_read_page, read_drive_file) that an agent must disambiguate by store. Descriptions do help assign each to its domain, but the multiple 'search' and 'read file' entry points create real selection friction.
Most names are snake_case verb_noun (krusch_git_list_repos, krusch_context_remember), which is readable and consistent within groups. However, prefixing is inconsistent—some tools carry the krusch_ prefix and others (get_agent_steering, generate_color_palette, css_to_tailwind, read_drive_file) do not, and a few are noun-first rather than verb-first.
At 39 tools this is well above the comfortable 3-15 range and heavy even for a multi-engine stack. Several domains (git search, fs search, drive, design templates) each contribute clusters that make the overall surface feel sprawling rather than crisp.
The major domains have strong lifecycle coverage: context memory has retrieve/remember/revise/nudge/health, the task flow covers stage/status/diff/apply/explain/reject/abort, and drive covers search/read/write/list/status. Minor gaps exist (no explicit drive delete, git is read-only by design), but agents can work around them.
Maintenance
Related MCP Connectors
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
Persistent, inspectable memory for AI agents with lineage, correction, and a hosted MCP endpoint.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Related MCP Servers
- AlicenseBqualityDmaintenanceA local-first MCP server that provides AI agents with safe codebase access through file discovery, hybrid lexical-semantic search, and project introspection. It features durable local memory and semantic indexing while keeping all data and processing entirely on your local machine.7427 npm6MIT
- AlicenseAqualityCmaintenanceMCP server providing structured continuity memory for AI coding agents, tracking decisions, open loops, and session state in local SQLite. Enables agents to resume work from verified state across sessions without replaying transcripts.17Apache 2.0
- AlicenseNot gradedqualityBmaintenanceLocal-first code intelligence and safety layer for AI coding agents. MCP server exposes dependency graph, impact analysis, and AST-compressed repo context, backed by typed local memory, patch-scope safety gates, and git-independent transaction rollback.1MIT
- AlicenseNot gradedqualityDmaintenanceLocal MCP server for persistent, searchable agent memory using SQLite FTS5, replacing flat MEMORY.md files with efficient full-text search and workspace context caching.GPL 3.0