# steipete/oracle

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/steipete-oracle).**

2,548 stars · 261 forks · TypeScript · MIT

## Links

- GitHub: https://github.com/steipete/oracle
- Homepage: https://askoracle.dev
- awesome-repositories: https://awesome-repositories.com/repository/steipete-oracle.md

## Topics

`agents` `ai` `anthropic` `gemini-pro` `gpt-5-pro` `openai` `opus` `sonnet`

## Description

Oracle is an LLM API gateway client and prompt orchestrator designed to route requests between official API endpoints and automated web browser channels. It functions as a context manager and session logger, bundling local files and prompts into requests while maintaining a history of interactions.

The system distinguishes itself through a request router that can redirect traffic to alternate endpoints, such as self-hosted gateways or proxy services. It includes a token estimator that calculates request size and predicts costs using local summaries without making network calls.

The project provides capabilities for AI context management via glob-based file filtering and preference management for storing engine, model, and prompt settings. It also features session history management to list, replay, or prune past interactions from local storage.

## Tags

### Artificial Intelligence & ML

- [Large Language Model Connectors](https://awesome-repositories.com/f/artificial-intelligence-ml/large-language-model-connectors.md) — Connects local data and custom settings to LLM APIs through configurable gateways and proxy services.
- [File-Based Context Selection](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-context-optimization/file-based-context-selection.md) — Filters local files using glob patterns to bundle relevant document context for LLM requests.
- [LLM Context Compilers](https://awesome-repositories.com/f/artificial-intelligence-ml/code-generation-assistants/documentation-generation/llm-context-compilers.md) — Filters local files via glob patterns to provide specific document context to large language models.
- [LLM Gateways](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-gateways.md) — Acts as a request router that redirects traffic between official API endpoints and automated browser channels.
- [Prompt Engineering](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-engineering.md) — Combines local files and custom prompts to provide language models with specific context for complex tasks.
- [Prompt Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-orchestration.md) — Bundles local files and prompts into requests for LLMs with support for custom API endpoints.
- [Session History Retrieval](https://awesome-repositories.com/f/artificial-intelligence-ml/conversational-session-management/multi-session-context-synthesizers/session-history-retrieval.md) — Provides a system to record and retrieve historical interaction data to restore or review session context. ([source](https://cdn.jsdelivr.net/gh/steipete/oracle@main/README.md))
- [LLM Token Counters](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-token-counters.md) — Calculates total request size and predicts costs for LLM interactions using local token counting.

### Development Tools & Productivity

- [Prompt File Packers](https://awesome-repositories.com/f/development-tools-productivity/prompt-file-packers.md) — Bundles local project files into AI prompts using pattern-based inclusion and exclusion to optimize context. ([source](https://cdn.jsdelivr.net/gh/steipete/oracle@main/README.md))
- [Input Token Estimators](https://awesome-repositories.com/f/development-tools-productivity/developer-utilities-libraries/workflow-productivity-enhancers/developer-analytics/codebase-metrics/codebase-size-and-token-count-reporters/codebase-size-and-token-count-reporters/cli-token-counters/input-token-estimators.md) — Calculates potential request size and predicts costs using a local token estimation mechanism.
- [Glob Pattern Selectors](https://awesome-repositories.com/f/development-tools-productivity/file-pattern-matching/regex-based-file-selection/glob-pattern-selectors.md) — Uses glob patterns and exclusion rules to filter which local files are included in an AI prompt. ([source](https://cdn.jsdelivr.net/gh/steipete/oracle@main/README.md))

### DevOps & Infrastructure

- [Request Redirection](https://awesome-repositories.com/f/devops-infrastructure/air-gapped-deployment-tools/registry-mirroring/request-redirection.md) — Implements request redirection to switch between official API endpoints and browser-based automation.

### Networking & Communication

- [API Endpoint Routing](https://awesome-repositories.com/f/networking-communication/api-endpoint-routing.md) — Provides the capability to redirect LLM API requests to custom server addresses or proxy services. ([source](https://cdn.jsdelivr.net/gh/steipete/oracle@main/README.md))
- [Prompt Payloads](https://awesome-repositories.com/f/networking-communication/email-address-validators/email-content-parsing/ai-powered-content-extraction/document-content-extraction/local-file-content-extraction/prompt-payloads.md) — Combines user text and local file contents into a single payload for large language model processing.

### Web Development

- [API and Browser Channel Routing](https://awesome-repositories.com/f/web-development/browser-to-ai-api-routing/api-and-browser-channel-routing.md) — Allows switching between official APIs and automated browser channels to access different account levels. ([source](https://cdn.jsdelivr.net/gh/steipete/oracle@main/README.md))

### Software Engineering & Architecture

- [Engine Routing Configurations](https://awesome-repositories.com/f/software-engineering-architecture/configuration-driven-rule-engines/engine-routing-configurations.md) — Directs requests to different API endpoints or browser channels based on a local persistent settings file.

### System Administration & Monitoring

- [Replayable Session Logs](https://awesome-repositories.com/f/system-administration-monitoring/ai-session-monitoring/session-replays/replayable-session-logs.md) — Records every request and response to a local storage system for later retrieval and replay.
- [Pre-Request Cost Estimation](https://awesome-repositories.com/f/system-administration-monitoring/usage-monitoring/token-usage-analytics/token-cost-calculators/token-cost-calculators/pre-request-cost-estimation.md) — Calculates total token usage for bundled prompts to predict API costs before sending requests.