Meilisearch vs wicked-brain
Side-by-side comparison to help you choose.
| Feature | Meilisearch | wicked-brain |
|---|---|---|
| Type | API | Repository |
| UnfragileRank | 42/100 | 32/100 |
| Adoption | 1 | 0 |
| Quality | 0 | 0 |
| Ecosystem |
| 0 |
| 1 |
| Match Graph | 0 | 0 |
| Pricing | Free | Free |
| Capabilities | 13 decomposed | 11 decomposed |
| Times Matched | 0 | 0 |
Implements keyword search using LMDB-backed inverted indexes (word_docids and word_pair_proximity_docids databases) built during parallel document extraction. The charabia tokenization layer automatically handles typos and misspellings with configurable Levenshtein distance thresholds, enabling users to find documents even with spelling errors. Search queries are parsed and matched against pre-computed word and word-pair proximity structures for sub-50ms response times.
Unique: Uses charabia tokenization with configurable Levenshtein distance thresholds integrated directly into the indexing pipeline, rather than post-query fuzzy matching. LMDB persistence provides memory-mapped access without separate database dependencies, and word-pair proximity indexes enable phrase-aware ranking without storing full positional data.
vs alternatives: Faster than Elasticsearch for typo-tolerant search on small-to-medium datasets because it optimizes for sub-50ms latency with minimal operational complexity, while Elasticsearch requires tuning fuzzy query parameters and managing cluster state.
Implements semantic search by storing document embeddings in the arroy vector index (HNSW-based approximate nearest neighbor search). Supports embeddings from OpenAI, HuggingFace, or Ollama via configurable embedding providers. Hybrid search combines keyword and semantic results using a weighted semanticRatio parameter (0.0-1.0) that blends BM25 keyword scores with vector similarity scores, enabling semantic understanding without abandoning keyword precision.
Unique: Integrates arroy (HNSW vector index) directly into the indexing pipeline with configurable embedding providers (OpenAI, HuggingFace, Ollama), enabling semantic search without external vector databases. The semanticRatio parameter allows fine-grained control over keyword-semantic blending at query time without reindexing, unlike systems that require separate vector stores.
vs alternatives: Simpler than Pinecone or Weaviate for hybrid search because it co-locates keyword and vector indexes in a single system, eliminating cross-service latency and synchronization complexity, while maintaining sub-50ms query times.
Implements document processing through a parallel extraction architecture in the milli crate that tokenizes, embeds, and indexes documents concurrently. The pipeline processes documents in batches, extracting text fields, generating embeddings (if configured), building inverted indexes, and creating vector indexes in parallel. Parallelization is transparent to the user; document batches are automatically distributed across CPU cores.
Unique: Implements parallel extraction in milli with automatic batching and distribution across CPU cores, eliminating the need for external parallelization frameworks. Tokenization, embedding, and indexing are pipelined for maximum throughput.
vs alternatives: Faster than sequential indexing or external parallelization frameworks because parallelization is built into the indexing pipeline and optimized for search workloads, achieving higher throughput on multi-core systems.
Implements data export through dump and export endpoints that serialize the entire index (documents, settings, indexes) to a portable format. Dumps can be imported into another Meilisearch instance, enabling backup, migration, and disaster recovery. Exports are performed asynchronously via the task queue, with progress tracking.
Unique: Provides asynchronous dump/export via the task queue with progress tracking, enabling large-scale backups without blocking the search engine. Dumps are portable and can be imported into other Meilisearch instances.
vs alternatives: Simpler than Elasticsearch snapshot/restore because dumps are self-contained files that don't require external storage backends; migration is as simple as downloading and uploading a dump file.
Uses LMDB (Lightning Memory-Mapped Database) as the underlying storage engine for all indexes, providing durability, ACID transactions, and memory-mapped file access. LMDB enables fast random access to index data without loading entire indexes into memory. Storage is organized into multiple databases (word_docids, word_pair_proximity_docids, facet_id_*_docids, vector indexes) for efficient querying.
Unique: Uses LMDB for all index storage, providing memory-mapped access and ACID transactions without external database dependencies. Multiple databases (word_docids, proximity_docids, facet indexes, vector indexes) are organized for efficient querying.
vs alternatives: More efficient than RocksDB or LevelDB for search workloads because LMDB's memory-mapped approach provides faster random access and lower memory overhead, while maintaining durability.
Implements document ingestion through the IndexScheduler task queue, which batches write operations (document additions, deletions, index creation, settings changes) and processes them asynchronously in the background. The parallel extraction pipeline in the milli crate processes documents through tokenization, embedding generation, and index construction in parallel, with automatic batching for efficiency. Task status is tracked and exposed via the Task Management API, enabling non-blocking document uploads.
Unique: Combines IndexScheduler task orchestration with parallel extraction in milli to automatically batch and process documents without explicit queue management. LMDB persistence ensures durability, and the task API provides visibility into indexing progress without polling external job systems.
vs alternatives: More integrated than using Celery or Bull for document indexing because the task queue is built into Meilisearch and optimized for search workloads, eliminating the need for separate message brokers and reducing operational complexity.
Implements filtering through a filter-parser that converts complex filter expressions into a FilterCondition abstract syntax tree (AST). Supports boolean operators (AND, OR, NOT), comparison operators (=, !=, <, >, <=, >=), range queries, and nested conditions. Filters are evaluated during search execution against indexed document fields, enabling precise result narrowing without separate filtering passes.
Unique: Uses a dedicated filter-parser that builds an AST for complex expressions, enabling efficient evaluation during search without re-parsing. Filters are integrated into the search query execution path, not applied post-hoc, reducing latency and enabling filter-aware ranking.
vs alternatives: More expressive than simple field-value filtering in systems like Algolia because it supports arbitrary boolean combinations and nested conditions, while remaining faster than Elasticsearch's Query DSL because filters are evaluated against pre-computed indexes.
Implements faceted navigation by pre-computing facet distributions during indexing using facet_id_*_docids databases. When a search is executed, facet counts are computed from the filtered result set without scanning all documents. Supports hierarchical facets and configurable facet ordering (alphabetical, count-based). Facet results are returned alongside search results, enabling drill-down navigation.
Unique: Pre-computes facet distributions during indexing (facet_id_*_docids databases) and evaluates them at query time against the filtered result set, enabling instant facet updates without full document scans. Facet counts are context-aware, reflecting the current search and filter state.
vs alternatives: Faster than Elasticsearch facet aggregations on large datasets because facet indexes are pre-built and facet computation is optimized for the filtered result set, not the entire index.
+5 more capabilities
Indexes markdown files containing code skills and knowledge into a local SQLite database with FTS5 (Full-Text Search 5) enabled, enabling semantic keyword matching without vector embeddings or external infrastructure. The system parses markdown structure (headings, code blocks, metadata) and builds inverted indices for fast retrieval of skill documentation by natural language queries. No external vector DB or embedding service required — all indexing and search happens locally.
Unique: Uses SQLite FTS5 for keyword-based retrieval instead of vector embeddings, eliminating dependency on external embedding services (OpenAI, Cohere) and vector databases while maintaining sub-millisecond local search performance
vs alternatives: Simpler and faster to set up than Pinecone/Weaviate RAG stacks for developers who prioritize zero infrastructure over semantic similarity
Retrieves indexed skills from the local SQLite database and injects them into the context window of AI coding CLIs (Claude Code, Cursor, Gemini CLI, GitHub Copilot) as formatted markdown or structured prompts. The system acts as a middleware layer that intercepts queries, searches the skill index, and prepends relevant documentation to the AI's input context before sending to the LLM. Supports multiple CLI integrations through adapter patterns.
Unique: Implements RAG-like behavior without vector embeddings by using FTS5 keyword matching and injecting matched skills directly into CLI context windows, designed specifically for AI coding assistants rather than generic LLM applications
vs alternatives: Lighter weight than full RAG pipelines (no embedding model, no vector DB) while still enabling skill-aware code generation in popular AI CLIs
Provides a command-line interface for managing the skill library (add, remove, search, list, export) without requiring programmatic API calls. Commands include `wicked-brain add <file>`, `wicked-brain search <query>`, `wicked-brain list`, `wicked-brain export`, enabling developers to manage skills from the terminal. Supports piping and scripting for automation.
Meilisearch scores higher at 42/100 vs wicked-brain at 32/100. Meilisearch leads on adoption and quality, while wicked-brain is stronger on ecosystem.
Need something different?
Search the match graph →© 2026 Unfragile. Stronger through disorder.
Unique: Provides a full-featured CLI for skill management (add, search, list, export) enabling terminal-based workflows and shell script integration without requiring a GUI or API client
vs alternatives: More scriptable and automation-friendly than GUI-based knowledge management tools
Provides a structured system for organizing, storing, and versioning coding skills as markdown files with optional metadata (tags, difficulty, language, category). Skills are stored in a flat or hierarchical directory structure and can be edited directly in any text editor. The system tracks which skills are indexed and provides utilities to add, update, and remove skills from the index without requiring a database UI or special tooling.
Unique: Treats skills as first-class markdown files with Git versioning rather than database records, enabling developers to manage their knowledge base using standard text editors and version control workflows
vs alternatives: More portable and version-control-friendly than proprietary knowledge base tools (Notion, Obsidian plugins) while remaining compatible with standard developer workflows
Executes all knowledge indexing and retrieval operations locally on the developer's machine using SQLite FTS5, eliminating the need for external services, API keys, or cloud infrastructure. The entire skill database is stored as a single SQLite file that can be backed up, versioned, or shared via Git. No network calls, no rate limits, no vendor lock-in — all operations complete in milliseconds on local hardware.
Unique: Deliberately avoids external dependencies (vector DBs, embedding APIs, cloud services) by using only SQLite FTS5, making it the only RAG-adjacent system that requires zero infrastructure setup or API credentials
vs alternatives: Eliminates operational complexity and cost of vector database services (Pinecone, Weaviate) while maintaining offline-first privacy guarantees that cloud-based RAG systems cannot provide
Provides an extensible adapter pattern for integrating the skill library with multiple AI coding CLIs through standardized interfaces. Each CLI adapter handles the specific protocol, context format, and API of its target tool (Claude Code's prompt format, Cursor's context injection, Gemini CLI's request structure). New adapters can be added by implementing a simple interface without modifying core indexing logic.
Unique: Uses adapter pattern to abstract CLI-specific integration details, allowing a single skill library to work across Claude Code, Cursor, Gemini CLI, and custom tools without duplicating indexing or retrieval logic
vs alternatives: More flexible than CLI-specific plugins because adapters are decoupled from core indexing, enabling skill library reuse across tools without reimplementing search
Converts natural language queries into FTS5 search expressions by tokenizing, normalizing, and optionally expanding queries with synonyms or related terms. The system handles common query patterns (e.g., 'how do I X' → search for skill tags matching X) and applies FTS5 operators (AND, OR, phrase matching) to improve precision. No machine learning or semantic models — purely lexical matching with heuristic query expansion.
Unique: Implements heuristic-based query expansion for FTS5 to handle natural language variations without semantic embeddings, using rule-based synonym mapping and query pattern recognition
vs alternatives: Simpler and faster than semantic search (no embedding inference latency) while still handling common query variations through configurable synonym expansion
Parses markdown skill files to extract structured metadata (title, description, tags, language, difficulty, category) from frontmatter (YAML/TOML) or markdown conventions (heading levels, code fence language tags). Metadata is indexed alongside skill content, enabling filtered searches (e.g., 'find all Python skills tagged with async'). Supports custom metadata fields through configuration.
Unique: Extracts metadata from markdown structure (YAML frontmatter, code fence language tags, heading levels) rather than requiring a separate metadata file, keeping skills self-contained and editable in any text editor
vs alternatives: More portable than database-based metadata (Notion, Obsidian) because metadata lives in the markdown file itself and is version-controllable
+3 more capabilities