airkjw/claude-mem
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(gemini): update Gemini model types and implement rate limiting for free tier

Browse Source 
- Changed Gemini model types to 'gemini-2.5-flash-lite', 'gemini-2.5-flash', and 'gemini-3-flash'.
- Introduced RPM limits for free tier models with a maximum of 10 RPM for 'gemini-2.5-flash-lite' and 5 RPM for the others.
- Added rate limiting enforcement in the GeminiAgent class, which waits based on the model's RPM limit.
- Updated getGeminiConfig to include billingEnabled setting, allowing users to skip rate limiting if billing is enabled.
- Modified ContextSettingsModal to reflect new model options and added a toggle for enabling billing.
- Updated default settings to use the new model and billing configuration.
This commit is contained in:
Alex Newman
2025-12-25 19:30:46 -05:00
parent b2b14a1b95
commit 7827226ed6
15 changed files with 227 additions and 151 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/public/usage/gemini-provider.mdx
+38 -13
View File
@@ -7,9 +7,9 @@ description: "Use Google's Gemini API as an alternative to Claude for observatio
Claude-mem supports Google's Gemini API as an alternative to the Claude Agent SDK for extracting observations from your sessions. This can significantly reduce costs since Gemini offers a generous free tier.
<Note>
**Free Tier Available**: Google provides 60 requests per minute and 1 million tokens per month at no cost. No billing information required.
</Note>
<Warning>
**Free Tier Rate Limits**: Without billing enabled, Gemini has strict rate limits (5-10 RPM). Enable billing on your Google Cloud project to unlock 1000-4000 RPM while still using the free quota.
</Warning>
## Why Use Gemini?
@@ -28,7 +28,7 @@ Claude-mem supports Google's Gemini API as an alternative to the Claude Agent SD
6. Copy and securely store the generated API key
<Tip>
Billing information is generally not required to use the free tier.
**No billing required** to get started, but we recommend enabling billing to unlock higher rate limits (1000-4000 RPM vs 5-10 RPM) while still using the free quota.
</Tip>
## Configuration
@@ -39,7 +39,8 @@ Billing information is generally not required to use the free tier.
|---------|--------|---------|-------------|
| `CLAUDE_MEM_PROVIDER` | `claude`, `gemini` | `claude` | AI provider for observation extraction |
| `CLAUDE_MEM_GEMINI_API_KEY` | string | — | Your Gemini API key |
| `CLAUDE_MEM_GEMINI_MODEL` | `gemini-2.0-flash-exp`, `gemini-1.5-flash`, `gemini-1.5-pro` | `gemini-2.0-flash-exp` | Gemini model to use |
| `CLAUDE_MEM_GEMINI_MODEL` | `gemini-2.5-flash-lite`, `gemini-2.5-flash`, `gemini-3-flash` | `gemini-2.5-flash-lite` | Gemini model to use |
| `CLAUDE_MEM_GEMINI_BILLING_ENABLED` | `true`, `false` | `false` | Skip rate limiting if billing is enabled on Google Cloud |
### Using the Settings UI
@@ -59,7 +60,8 @@ Edit `~/.claude-mem/settings.json`:
{
"CLAUDE_MEM_PROVIDER": "gemini",
"CLAUDE_MEM_GEMINI_API_KEY": "your-api-key-here",
"CLAUDE_MEM_GEMINI_MODEL": "gemini-2.0-flash-exp"
"CLAUDE_MEM_GEMINI_MODEL": "gemini-2.5-flash-lite",
"CLAUDE_MEM_GEMINI_BILLING_ENABLED": "true"
}
```
@@ -73,11 +75,11 @@ The settings file takes precedence over the environment variable.
## Available Models
| Model | Speed | Capability | Notes |
|-------|-------|------------|-------|
| `gemini-2.0-flash-exp` | Fastest | Good | Default, recommended for most usage |
| `gemini-1.5-flash` | Fast | Good | Stable release |
| `gemini-1.5-pro` | Slower | Best | Use for complex observation extraction |
| Model | Free Tier RPM | Notes |
|-------|--------------|-------|
| `gemini-2.5-flash-lite` | 10 | Default, recommended for free tier (highest RPM) |
| `gemini-2.5-flash` | 5 | Higher capability, lower rate limit |
| `gemini-3-flash` | 5 | Latest model, lower rate limit |
## Provider Switching
@@ -129,9 +131,32 @@ Either:
### Rate Limiting
The free tier allows 60 requests per minute. If you hit rate limits:
Google has two rate limit tiers for free usage:
**Without billing (API key only):**
| Model | RPM | TPM |
|-------|-----|-----|
| gemini-2.5-flash-lite | 10 | 250K |
| gemini-2.5-flash | 5 | 250K |
| gemini-3-flash | 5 | 250K |
Claude-mem enforces these limits automatically with built-in delays between requests. Processing may be slower but stays within limits.
**With billing enabled (still free tier):**
| Model | RPM | TPM |
|-------|-----|-----|
| gemini-2.5-flash-lite | 4,000 | 4M |
| gemini-2.5-flash | 1,000 | 1M |
| gemini-3-flash | 1,000 | 1M |
<Tip>
**Recommended**: Enable billing on your Google Cloud project to unlock much higher rate limits. You won't be charged unless you exceed the generous free quota. This allows claude-mem to process observations instantly instead of waiting between requests.
</Tip>
If you hit rate limits:
- Claude-mem automatically falls back to Claude SDK
- Consider upgrading to a paid Gemini plan for higher limits
- Or switch back to Claude as your primary provider
### Observation Quality