infimium-agent
Active·★ 25·MIT·Updated 2026-10-05
Infimium provides a private context layer for AI agents, integrating web search, local documents, semantic code search, and dependency graphs. It aims to solve the problem of agents losing context in large codebases by offering targeted tools and persistent project memory.
#AI Agents#Context Management#Semantic Search#Code Analysis#Developer Tools#Knowledge Base#Local LLM#Workflow Automation
01
Features
01Private context layer for AI agents with a local Master Control Program (MCP) server
02Semantic code and document search utilizing local LLMs (Ollama) and vector database (ChromaDB)
03Automated dependency graph generation from code imports to understand relationships
04Persistent project memory across various agent interactions, chats, and IDE sessions
05Workspace federation for managing context and memory across multiple related repositories
02
Compatibility
Node.js
Runtime
Verified via docs
Docker
Deployment
Verified via docs
Ollama
LLM Runtime
Verified via docs
ChromaDB
Vector Database
Verified via docs
JavaScript
Code Indexing
Verified via docs
TypeScript
Code Indexing
Verified via docs
03
Quick start
1
$ git clone https://github.com/infimium-ai/infimium-agent.git
2
$ cd infimium-agent
3
$ ./scripts/setup.sh
04
Use cases
↳Enhancing AI agent performance in large codebases by providing targeted and accurate context
↳Integrating with IDEs (e.g., Cursor) and LLM platforms (e.g., Claude) to provide rich project context for coding assistants
↳Performing semantic code searches and understanding dependency graphs for complex development and refactoring tasks
↳Maintaining project-specific memory and context across different agent interactions and development sessions
↳Managing and correlating context for multiple interconnected repositories within a unified workspace
05
Alternatives
mori★ 32
mori MCP server — A shared memory layer for AI coding agents — one that compounds.
agents-remember★ 29
`Agents Remember` is a Drift-aware repository memory for coding agents in complex codebases. Captures what code can't say on its own! Retrieves memory by path, semantic search, and relationship (code-graph).
mex★ 1.8k
Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.
okf-agent-memory★ 827
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Comments
Log in to leave a comment
No comments yet. Be the first!