AgentIndex icon
AgentIndex
ToolsCategoriesTrendingNewCompare
Submit Tool
Home/
Compare/
rekal vs FunASR
rekal logo
rekal
★ 48
vs
FunASR logo
FunASR
★ 16.6k

rekal vs FunASR

rekal: rekal provides long-term memory for LLMs via an MCP server. It stores memories in a local SQLite file and retrieves them using hybrid search (BM25 keywords + vector semantics + recency decay). It works with any MCP-capable agent like Claude Code, Codex CLI, and OpenCode.; FunASR: FunASR is a fundamental end-to-end speech recognition toolkit. It offers industrial-grade speech recognition, being 170x faster than Whisper, supporting over 50 languages, and integrating features like speaker diarization, emotion detection, and streaming.

01

TL;DR

rekal logoChoose rekal if…

Persistent memory for coding agents across sessions to remember user preferences and decisions

FunASR logoChoose FunASR if…

Meeting transcription with speaker labels, timestamps, and punctuation

02

Side-by-Side Comparison

Field
rekal logorekal
FunASR logoFunASR
Category
RAG / Knowledge Base
Voice / Speech
Stars
★ 48
★ 16.6k
License
MIT
MIT
Updated
2w ago
2d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
llm, mcp, mcp-server
asr, audio, chinese
03

Features

rekal logorekal
01Local SQLite storage, no cloud or API keys
02Hybrid search combining BM25 keywords, vector semantics, and recency decay
03MCP server compatible with various coding agents
04Comprehensive tool-based memory management (store, search, update, delete, prune)
05Smart write operations with supersede and linking for knowledge evolution
FunASR logoFunASR
01Extremely fast (170x faster than Whisper)
02Supports 50+ languages
03Built-in Speaker Diarization
04Emotion Detection
05Streaming ASR and vLLM Acceleration
04

Use Cases

rekal logorekal
↳Persistent memory for coding agents across sessions to remember user preferences and decisions
↳Storing project-specific knowledge and conventions without external services
↳Maintaining a searchable history of agent interactions and decisions
FunASR logoFunASR
↳Meeting transcription with speaker labels, timestamps, and punctuation
↳Deployment as an OpenAI-compatible API server
↳Integration with AI agents (e.g., Claude, LangChain, Dify, AutoGen)
05

Best For

rekal logorekal
TrendingRAG / Knowledge BaseMemory & Context
FunASR logoFunASR
Most PopularVoice / SpeechLLM Infra
FAQ

FAQ

What is the difference between rekal and FunASR?
Both rekal and FunASR are in the RAG / Knowledge Base category. rekal has 48 stars, while FunASR has 16.6k stars.
Which is better, rekal or FunASR?
The best choice depends on your use case. Choose rekal if Persistent memory for coding agents across sessions to remember user preferences and decisions, and FunASR if Meeting transcription with speaker labels, timestamps, and punctuation.
Is rekal free or open source?
Yes, rekal is open source on GitHub (MIT).
Is FunASR free or open source?
Yes, FunASR is open source on GitHub (MIT).
→

Related

Alternatives to rekal →Alternatives to FunASR →rekal details →FunASR details →OpenClaw vs FunASR →
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
QYSGitHubBuy me a coffee ☕

Browse by Category

Code AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.