claude-mem
claude-mem records what your coding agent does in a session, compresses it with a model, and feeds the relevant parts back into the next session, so Claude Code, Codex, OpenCode and the rest pick up where they left off. The compression step runs on whichever provider you choose, and Opper is one of its presets: select it, add your key, and memory runs on any of 700+ models, with a small model as the default to keep high-volume extraction cheap.
claude-memoninConnect claude-mem to Opper
Add Opper in claude-mem
In claude-mem (v13.32 or later), set CLAUDE_MEM_PROVIDER to openai-compatible and CLAUDE_MEM_OPENAI_COMPAT_PRESET to opper in ~/.claude-mem/settings.json, then add your key as CLAUDE_MEM_OPENAI_COMPAT_API_KEY.
Run claude-mem across our providers
On Opper, claude-mem can reach every provider in the catalogue. Pick where your inference runs, keep it in the EU when you need to, and use zero data retention on supported routes.
More apps on Opper
Claude Code
Anthropic's terminal coding agent. Run it on any model on Opper, not just Claude.
opper launch claude
Codex
OpenAI's open-source coding CLI. Run it on any model on Opper.
opper launch codex
DeepSeek Harness
DeepSeek's open-source coding agent. Add Opper as a custom provider to run it on any model, not just DeepSeek's.
OpenAI-compatible