BerriAI/litellm - GitHub vs Claude Mem
Side-by-side comparison · Updated October 2026
| Description | LiteLLM is an AI gateway and Python SDK from Berrie AI Incorporated, published in the BerriAI GitHub repository. The SDK provides a common interface for model calls inside Python applications. The proxy gateway centralizes access for a team, with virtual keys, model routing, spend tracking, budgets and an administration interface. The official documentation lists support for more than 100 model providers. Supported endpoints and features vary by integration, so verify your model’s streaming, tool-calling, image, audio or embedding requirements. The router supports retries, fallbacks and load balancing; observability integrations can send request data to tools such as Langfuse, LangSmith and OpenTelemetry. LiteLLM also provides an MCP gateway. It can connect upstream servers using Streamable HTTP, SSE or stdio, expose tools through a fixed gateway endpoint, and scope access by key, team or organization. This requires configuring the upstream servers and authentication; the gateway does not automatically grant access to third-party tools. Agent-to-agent integrations are documented separately. The open-source offering has no software license fee for self-hosting. Code outside the enterprise directory is MIT-licensed, while enterprise code has separate terms. Enterprise pricing is quoted by annual gateway request capacity, deployment architecture and support needs, rather than a per-token license charge. Model-provider charges and infrastructure costs still apply. Enterprise adds controls and support such as SSO, SCIM, audit logs and service-level agreements. Compare New API for another self-hosted gateway with provider-channel management and usage accounting. Evaluate a representative workload, inspect request logging and secret handling, test budget and failure behavior, and decide whether SDK integration or a shared gateway best fits your application. | Claude Code is powerful, but it starts every session with a blank slate. You explain your project structure, coding conventions, and past decisions over and over. Claude Mem fixes this by giving Claude Code a persistent memory layer. The plugin works as a lightweight MCP server that Claude Code connects to automatically. When you tell Claude something important — a naming convention, an architectural decision, a bug fix rationale — you can save it to memory with a simple command. On the next session, Claude Code loads those memories as context before it starts working. Memories are stored as structured files in your project directory. Each memory has a category (architecture, convention, decision, bugfix, todo) and a relevance scope (project-wide or directory-specific). This structure means Claude Code loads only relevant memories, keeping the context window clean. The plugin ships with automatic memory extraction too. When Claude Code finishes a task, Claude Mem can prompt it to save key learnings. This creates a growing knowledge base that gets smarter over time. After a week of use, Claude Code knows your project's patterns, your team's style, and your past debugging sessions. Installation takes about two minutes. Clone the repo, add it to your Claude Code MCP settings, and restart. No database to set up, no API keys to configure. Everything lives in your project's .claude-mem directory, which you can commit to git for team sharing. Claude Mem is free and open source. It works with any Claude Code setup — free tier, Pro, or Max. The memory format is plain Markdown, so you can read and edit memories directly if you want more control. |
| Category | Developer Tools | DeveloperApplication |
| Rating | No reviews | No reviews |
| Pricing | Open Source | Free |
| Starting Price | N/A | Free |
| Plans | — |
|
| Use Cases |
|
|
| Tags | AI gatewayPython SDKLLM routingMCP gatewayvirtual keys | claude-code-pluginpersistent-memorycontext-managementmcp-serverdeveloper-tools |
| Features | ||
| Python SDK for direct application integration | ||
| Shared AI proxy gateway and administration UI | ||
| More than 100 documented model-provider integrations | ||
| Virtual keys, users, teams, budgets and rate limits | ||
| Spend tracking and observability integrations | ||
| Router retries, fallbacks and load balancing | ||
| MCP gateway for Streamable HTTP, SSE and stdio upstreams | ||
| Key, team and organization MCP permissions | ||
| Separate enterprise identity, audit and support features | ||
| Persistent memory storage across Claude Code sessions with no re-explanation needed | ||
| Structured memory categories: architecture, convention, decision, bugfix, todo | ||
| Scoped relevance — project-wide or directory-specific memory loading | ||
| Automatic memory extraction prompts after task completion | ||
| Plain Markdown memory format that is human-readable and editable | ||
| MCP server integration — connects to Claude Code in two minutes | ||
| Git-friendly storage in .claude-mem directory for team sharing | ||
| Zero configuration — no database, no API keys, no external dependencies | ||
| Works with all Claude Code tiers: free, Pro, and Max | ||
| Growing knowledge base that accumulates project intelligence over time | ||
| View BerriAI/litellm - GitHub | View Claude Mem | |
Modify This Comparison
Also Compare
Explore more head-to-head comparisons with BerriAI/litellm - GitHub and Claude Mem.