The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
Openai proxy: allow system prompt from user (#2097)
Dev Khant716824860bd1
diff --git a/mem0/proxy/main.py b/mem0/proxy/main.pyindex f52177d0f..8689ef3e1 100644--- a/mem0/proxy/main.py+++ b/mem0/proxy/main.py@@ -149,7 +149,6 @@ class Completions:def _prepare_messages(self, messages: List[dict]) -> List[dict]:if not messages or messages[0]["role"] != "system":return [{"role": "system", "content": MEMORY_ANSWER_PROMPT}] + messages- messages[0]["content"] = MEMORY_ANSWER_PROMPTreturn messagesdef _async_add_to_memory(self, messages, user_id, agent_id, run_id, metadata, filters):diff --git a/pyproject.toml b/pyproject.tomlindex 3358cb149..60bc8f027 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -1,6 +1,6 @@[tool.poetry]name = "mem0ai"-version = "0.1.35"+version = "0.1.36"description = "Long-term memory for AI Agents"authors = ["Mem0 <[email protected]>"]exclude = [