Export or import your agent's personality, memory, settings, and data. ์์ด์ ํธ์ ์ธ๊ฒฉ, ๊ธฐ์ต, ์ค์ , ๋ฐ์ดํฐ๋ฅผ ๋ด๋ณด๋ด๊ฑฐ๋ ๊ฐ์ ธ์ต๋๋ค.
Export / ๋ด๋ณด๋ด๊ธฐ
Import / ๊ฐ์ ธ์ค๊ธฐ
๐ Drop ZIP file here or click to browse ZIP ํ์ผ์ ์ฌ๊ธฐ์ ๋๊ฑฐ๋ ํด๋ฆญํ์ธ์
๐ Update
Current: v
โก Engine Optimization / ์์ง ์ต์ ํ
Control how SalmAlm balances cost vs quality. All changes take effect immediately without restart.
์ถ์์ ๋น์ฉ๊ณผ ํ์ง ๊ท ํ์ ์กฐ์ ํฉ๋๋ค. ๋ชจ๋ ๋ณ๊ฒฝ์ ์ฌ์์ ์์ด ์ฆ์ ์ ์ฉ๋ฉ๋๋ค.
ON (recommended): Only sends relevant tools based on your message intent.
Chat/casual โ 0 tools (0 tok) ยท Weather/calendar โ 7-12 tools (~750 tok) ยท Coding โ 11 tools (~700 tok) OFF: Always sends all 62 tools every call โ ~7,750 tok overhead per request
ON: Before complex code/analysis tasks, injects a planning prompt that asks the AI to outline its approach before executing. Can improve accuracy for multi-step tasks. Cost:+~150 input tokens per complex request (~$0.002/call on Opus) OFF (default): AI plans naturally within its response. Sufficient for most tasks.
ON: After generating code or analysis, makes a second full LLM call to review and improve the response. Catches bugs, hallucinations, and incomplete answers. Cost:Doubles the cost for complex tasks (2x LLM calls). E.g., a coding response that costs $0.05 โ $0.10. Best for: Production code, security audits, critical analysis where accuracy matters more than speed. OFF (default): Single-pass generation. Faster and cheaper. Quality is still good for most tasks.
Controls when old messages are summarized to free up context space. Lower = more frequent compaction = lower cost per turn but may lose details. 15K (Aggressive): Compacts often. Best for cost savings. ~$0.01/turn avg on Opus 30K (Balanced): Good middle ground. ~$0.02/turn avg 60K (Relaxed): Keeps more history. ~$0.04/turn avg 120K (Maximum): Full context retention. Best for long coding sessions. ~$0.08/turn avg
When daily spending reaches this limit, the AI will stop processing new requests until the next day (UTC reset). Leave empty for no limit. Suggested values: Casual use: $1-2/day ยท Active use: $5-10/day ยท Heavy dev: $20-50/day
Click a model to switch. Pricing per 1M tokens (input / output).
๐ Auto Routing / ์๋ ๋ผ์ฐํ
SalmAlm automatically classifies each message by complexity and routes it to the optimal model.
This saves money by using cheap models for simple tasks and powerful models only when needed.
์ถ์์ ๊ฐ ๋ฉ์์ง์ ๋ณต์ก๋๋ฅผ ์๋ ๋ถ๋ฅํ์ฌ ์ต์ ์ ๋ชจ๋ธ๋ก ๋ผ์ฐํ ํฉ๋๋ค. ๊ฐ๋จํ ์์ ์ ์ ๋ ดํ ๋ชจ๋ธ์, ๋ณต์กํ ์์ ์๋ง ๊ฐ๋ ฅํ ๋ชจ๋ธ์ ์ฌ์ฉํ์ฌ ๋น์ฉ์ ์ ๊ฐํฉ๋๋ค.
๐ How does classification work? / ๋ถ๋ฅ๋ ์ด๋ป๊ฒ ์๋ํ๋์?
Greetings, short questions, casual chat. No tools needed.
์ธ์ฌ, ์งง์ ์ง๋ฌธ, ์ก๋ด. ๋๊ตฌ ๋ถํ์.
Default: Haiku โ $0.25/$1.25 per M tokens (cheapest)
Code review, analysis, summaries, search, translations.
์ฝ๋ ๋ฆฌ๋ทฐ, ๋ถ์, ์์ฝ, ๊ฒ์, ๋ฒ์ญ.
Default: Sonnet โ $3/$15 per M tokens (balanced)
System design, architecture, long reasoning, thinking mode tasks.
์์คํ ์ค๊ณ, ์ํคํ ์ฒ, ๊ธด ์ถ๋ก , thinking ๋ชจ๋ ์์ .
Default: Sonnet โ $3/$15 per M tokens. Set Opus for maximum quality ($15/$75).
๐ก Tip: Use /model opus in chat to temporarily override for a single session without changing these defaults.
๐ก ํ: ์ฑํ ์์ /model opus๋ก ์ด ๊ธฐ๋ณธ๊ฐ์ ๋ฐ๊พธ์ง ์๊ณ ํ์ฌ ์ธ์ ๋ง ์ผ์์ ์ผ๋ก ์ค๋ฒ๋ผ์ด๋ํ ์ ์์ต๋๋ค.
๐ฆ Ollama (Local LLM)
๐ API Keys
Enter API keys to enable providers. Keys are tested in real-time.
๐ฌ Debug Diagnostics
๐ Server Logs
๐
Enter to send ยท Shift+Enter newline ยท Ctrl+V paste ยท Drag&Drop files