capability
Local Llm agents
This page lists every AI agent in the MeshKore directory tagged with the Local Llm capability. Agents are sourced from public platforms (GitHub, Hugging Face, npm, PyPI, awesome-list curations, and direct submissions), normalized by the MeshKore worker, and ranked by GitHub stars. Each card links to the agent's profile with details on capabilities, framework, language, freshness, and source attribution.
31 agents in this capability · ranked by popularity
Top 31 Local Llm agents
Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention…
pi / senpi extension: structural code search (ast-grep), LSP intelligence (gopls/tsserver/marksman), bounded…
Hanseol - OpenAI-Compatible Coding Agent
Ollama adapter for TanStack AI local LLM chat, tool calling, and structured outputs.
Open-source multi-agent coding tool for your terminal. Powered by Ollama.
GEIANT Hive provider for OpenClaw — cryptographically-signed distributed local AI inference with EU AI Act…
Run Claude Code locally on the Bonsai 8B 1-bit MLX model.
MCP executor for Claude Code or Codex that offloads repetitive coding work to cheaper local or flat-rate…
Framework for efficient local LLM interaction
Ultra-fast local LLM inference with zero-config hardware-optimized speculative decoding.
39% faster TTFT, 67% less KV cache, zero config — autotune optimises local LLMs on Ollama, LM Studio, and MLX
Mask sensitive data in documents using a local OpenAI-compatible LLM
A unified interface for multiple LLM providers with image generation, speech-to-text, and function calling…
Generate and update agent config files from LM Studio models for VS Code Copilot, OpenCode, Pi, and Codex.
Standalone agentic framework for local LLMs via Ollama — reliable tool calling, session persistence, and loop…
100% local RAG for Obsidian, Zotero, and Claude Code — LightRAG + Ollama + MCP
MCP server for hot-swapping llama.cpp models in Claude Code sessions
Ask your codebase questions using Ollama and Mnemosyne -- zero-config local code search
Multi-agent coding system powered by local LLMs
Ollama inference provider for the NucleusIQ AI agent framework (official ollama Python SDK).
Validate structured outputs from LLMs with Ollama and automatic retries.
Bridge API service connecting Ollama with Model Context Protocol (MCP) servers
One command launcher for running OpenCode with a local llama.cpp model.
The Fastest Way to Audit Your RAG - Generate QA datasets & evaluate RAG systems in Colab, Jupyter, or CLI…
A sequence-based LLM orchestration framework
Multilingual Parallel Translation Platform with Reflection-based Improvement using Local LLMs
Generic LLM provider abstraction — Anthropic, OpenAI, Google, Ollama and any OpenAI-compatible local model
Find the best LLM that runs on your hardware
A configurable local chatbot library with lightweight memory indexing.
Badgr Auto — local OpenAI-compatible proxy that optimizes context, routes to cheapest model, and logs…
A lightweight Python SDK for using local and OpenAI-compatible LLMs.