adaptive-memory-multi-model-router 2.14.45 → 2.14.47

package/.env.example

@@ -1,303 +0,0 @@
-# =============================================================================
-# A3M Router - Adaptive Memory Multi-Model Router
-# Environment Configuration Template
-# =============================================================================
-#
-# Copy this file to .env and fill in your API keys.
-# At least one provider key is required for the router to function.
-# Providers without keys are automatically skipped at runtime.
-#
-# Usage:
-#   cp .env.example .env
-#   # Edit .env with your keys
-#   a3m-router start
-#
-# =============================================================================
-
-# =============================================================================
-# SECTION 1: PRIMARY PROVIDERS (Frontier / Most Commonly Used)
-# =============================================================================
-
-# OpenAI — GPT-4o, GPT-4o-mini, o1, o3, etc.
-# https://platform.openai.com/api-keys
-OPENAI_API_KEY=sk-...
-
-# Anthropic — Claude Sonnet 4, Opus, Haiku
-# https://console.anthropic.com/
-ANTHROPIC_API_KEY=sk-ant-...
-
-# Google / Gemini — Gemini 2.5 Flash/Pro, Gemma
-# https://aistudio.google.com/apikey
-GOOGLE_API_KEY=...
-
-# xAI — Grok-3, Grok-3-mini, Grok-2
-# https://console.x.ai
-XAI_API_KEY=...
-
-# =============================================================================
-# SECTION 2: FAST INFERENCE PROVIDERS (Cheap / Low-Latency)
-# =============================================================================
-
-# Groq — LPU-powered inference, very fast
-# https://console.groq.com/keys
-GROQ_API_KEY=gsk_...
-
-# Cerebras — Wafer-scale inference, ultra-fast
-# https://cloud.cerebras.ai/
-CEREBRAS_API_KEY=...
-
-# DeepInfra — Serverless inference, many open models
-# https://deepinfra.com/dash/api_keys
-DEEPINFRA_API_KEY=...
-
-# Together AI — Hosted open-source models
-# https://api.together.ai/settings/api-keys
-TOGETHER_API_KEY=...
-
-# Fireworks AI — Fast inference for open models
-# https://fireworks.ai/api-keys
-FIREWORKS_API_KEY=...
-
-# Novita AI — Low-cost LLM inference
-# https://novita.ai/settings
-NOVITA_API_KEY=...
-
-# SambaNova — Fast open-model inference
-# https://cloud.sambanova.ai/
-SAMBANOVA_API_KEY=...
-
-# Anyscale — Endpoints for open models
-# https://console.anyscale.com/
-ANYSCALE_API_KEY=...
-
-# =============================================================================
-# SECTION 3: MID-TIER / SPECIALTY PROVIDERS
-# =============================================================================
-
-# DeepSeek — DeepSeek-V3, DeepSeek-R1
-# https://platform.deepseek.com/api_keys
-DEEPSEEK_API_KEY=...
-
-# Mistral AI — Mistral Large, Small, Codestral, Ministral
-# https://console.mistral.ai/api-keys
-MISTRAL_API_KEY=...
-
-# Perplexity — Sonar models with online search
-# https://www.perplexity.ai/settings/api
-PERPLEXITY_API_KEY=...
-
-# Cohere — Command R+, Command A, embeddings
-# https://dashboard.cohere.com/api-keys
-COHERE_API_KEY=...
-
-# AI21 Labs — Jamba 1.5 models
-# https://studio.ai21.com/account/api-keys
-AI21_API_KEY=...
-
-# Replicate — Cloud for open-source models
-# https://replicate.com/account/api-tokens
-REPLICATE_API_KEY=...
-
-# Hugging Face — Inference API, Inference Endpoints
-# https://huggingface.co/settings/tokens
-HUGGINGFACE_API_KEY=hf_...
-# or use HF_API_TOKEN
-HF_API_TOKEN=hf_...
-
-# Writer — Palmyra models, full-stack AI platform
-# https://dev.writer.com/
-WRITER_API_KEY=...
-
-# OctoAI — Fast inference for open and custom models
-# https://octo.ai/
-OCTOAI_API_KEY=...
-
-# =============================================================================
-# SECTION 4: AI AGGREGATORS & ROUTERS
-# =============================================================================
-
-# OpenRouter — Aggregator with 200+ models, passthrough pricing
-# https://openrouter.ai/keys
-OPENROUTER_API_KEY=...
-
-# AI/ML API — Single API for 200+ models
-# https://aimlapi.com/
-AIMLAPI_KEY=...
-
-# =============================================================================
-# SECTION 5: ENTERPRISE CLOUD PROVIDERS
-# =============================================================================
-
-# Azure OpenAI — GPT models via Azure
-# https://portal.azure.com/
-AZURE_OPENAI_API_KEY=...
-# Also requires your Azure endpoint
-AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/
-
-# AWS Bedrock — Claude, Llama, Mistral via AWS
-# https://console.aws.amazon.com/bedrock/
-AWS_ACCESS_KEY_ID=...
-AWS_SECRET_ACCESS_KEY=...
-# Optional: set default region
-AWS_REGION=us-east-1
-
-# Google Vertex AI — Gemini, Claude via GCP
-# https://console.cloud.google.com/vertex-ai
-# Path to service account JSON key file
-GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account-key.json
-
-# IBM watsonx — Granite, Llama, Mistral on IBM Cloud
-# https://cloud.ibm.com/watsonx
-WATSONX_API_KEY=...
-WATSONX_PROJECT_ID=...
-WATSONX_URL=https://us-south.ml.cloud.ibm.com
-
-# Cloudflare Workers AI — Serverless AI inference
-# https://dash.cloudflare.com/profile/api-tokens
-CLOUDFLARE_API_TOKEN=...
-CLOUDFLARE_ACCOUNT_ID=...
-
-# =============================================================================
-# SECTION 6: NVIDIA PLATFORMS
-# =============================================================================
-
-# NVIDIA NIM / API Catalog — Free tier for many open models
-# https://build.nvidia.com/
-NVIDIA_API_KEY=nvapi-...
-
-# NVIDIA AI Foundation — Endpoints for NeMo, Llama, etc.
-# Also uses NVIDIA_API_KEY above
-
-# =============================================================================
-# SECTION 7: CHINESE / ASIAN PROVIDERS
-# =============================================================================
-
-# Zhipu AI (GLM) — GLM-4 series
-# https://open.bigmodel.cn/usercenter/apikeys
-ZHIPU_API_KEY=...
-
-# Alibaba Qwen (DashScope) — Qwen-Max, Qwen-Plus, Qwen-Turbo
-# https://dashscope.console.aliyun.com/
-DASHSCOPE_API_KEY=...
-
-# Moonshot AI (Kimi) — Long-context models (128K)
-# https://platform.moonshot.cn/
-MOONSHOT_API_KEY=...
-
-# 01.AI (Yi) — Yi-Lightning, Yi-Large, Yi-Medium
-# https://platform.lingyiwanwu.com/
-YI_API_KEY=...
-
-# Baichuan AI — Baichuan4, Baichuan3-Turbo
-# https://platform.baichuan-ai.com/
-BAICHUAN_API_KEY=...
-
-# MiniMax — MiniMax-Text-01, abab models
-# https://platform.minimax.chat/
-MINIMAX_API_KEY=...
-
-# StepFun (Step) — Step-1, Step-2 models
-# https://platform.stepfun.com/
-STEPFUN_API_KEY=...
-
-# ByteDance (Doubao) — Doubao-pro, Doubao-lite
-# https://console.volcengine.com/ark
-ARK_API_KEY=...
-
-# Tencent (Hunyuan) — Hunyuan large models
-# https://console.cloud.tencent.com/hunyuan
-TENCENT_API_KEY=...
-
-# Baidu (ERNIE) — ERNIE 4.0, ERNIE-Bot
-# https://console.bce.baidu.com/qianfan/
-BAIDU_API_KEY=...
-BAIDU_SECRET_KEY=...
-
-# =============================================================================
-# SECTION 8: EUROPEAN & PRIVACY-FOCUSED PROVIDERS
-# =============================================================================
-
-# Aleph Alpha — Luminous models (GDPR-compliant)
-# https://www.aleph-alpha.com/
-ALEPH_ALPHA_API_KEY=...
-
-# Deepset — Haystack Cloud, model endpoints
-# https://cloud.deepset.ai/
-DEEPSET_API_KEY=...
-
-# Lepton AI — Fast, affordable inference
-# https://lepton.ai/
-LEPTON_API_KEY=...
-
-# Mistral AI (also listed above, European-based)
-# MISTRAL_API_KEY=...
-
-# =============================================================================
-# SECTION 9: EMBEDDINGS & SPECIALTY PROVIDERS
-# =============================================================================
-
-# Jina AI — Embeddings, Reranker, Reader API
-# https://jina.ai/
-JINA_API_KEY=...
-
-# Voyage AI — Specialized embedding models
-# https://www.voyageai.com/
-VOYAGE_API_KEY=...
-
-# Cohere (also listed above — embeddings + generation)
-# COHERE_API_KEY=...
-
-# Deepgram — Speech-to-text, text-to-speech, LLM (Nova-2)
-# https://console.deepgram.com/
-DEEPGRAM_API_KEY=...
-
-# =============================================================================
-# SECTION 10: ADDITIONAL / EMERGING PROVIDERS
-# =============================================================================
-
-# GooseAI — API for open models (deprecated but still supported)
-GOOSEAI_API_KEY=...
-
-# aiXcoder — Code-specialized LLM API
-AIXCODER_API_KEY=...
-
-# Infinity — Embedding serving (self-hosted)
-INFINITY_API_KEY=...
-
-# Laminar — LLM observability + routing
-LAMINAR_API_KEY=...
-
-# Fireworks (also listed above)
-# FIREWORKS_API_KEY=...
-
-# CommandCode — Coding agent API
-COMMANDCODE_API_KEY=...
-
-# =============================================================================
-# SECTION 11: LOCAL / SELF-HOSTED (No API keys needed)
-# =============================================================================
-#
-# These run locally and require no environment variables:
-#
-# Ollama           — http://127.0.0.1:11434      (no key)
-# LM Studio        — http://127.0.0.1:1234       (no key)
-# vLLM (local)     — http://127.0.0.1:8000       (no key)
-# LocalAI          — http://127.0.0.1:8080       (no key)
-# llama.cpp server — http://127.0.0.1:8080       (no key)
-# Text Generation Inference (TGI) — http://127.0.0.1:8080 (no key)
-#
-# =============================================================================
-
-# =============================================================================
-# SECTION 12: SERVER CONFIGURATION
-# =============================================================================
-
-# Port and host for the A3M Router proxy server
-PORT=3000
-HOST=0.0.0.0
-
-# Optional: API key required to access the router itself
-# A3M_API_KEY=router-secret-key
-
-# Logging level: debug | info | warn | error
-LOG_LEVEL=info

package/.github/DISCUSSIONS_WELCOME.md

@@ -1,27 +0,0 @@
-# Welcome to A3M Router Discussions!
-
-## 🎯 What is A3M Router?
-A3M Router is an open-source LLM router that runs queries across **47+ providers in parallel**, scores responses by confidence, and returns the best result. No sequential fallback. No vendor lock-in.
-
-## 💬 Discussion Categories
-- **Show and Tell** — Share what you've built with A3M Router
-- **Q&A** — Ask questions about usage, configuration, deployment
-- **Ideas** — Feature requests and suggestions
-- **Announcements** — Release notes and updates
-
-## 🔗 Quick Links
-- [GitHub](https://github.com/Das-rebel/a3m-router)
-- [npm](https://www.npmjs.com/package/adaptive-memory-multi-model-router)
-- [Documentation](https://github.com/Das-rebel/a3m-router#readme)
-- [Benchmark Results](https://github.com/Das-rebel/a3m-router/blob/main/docs/BENCHMARK.md)
-
-## 🚀 Getting Started
-```bash
-npx a3m-router "What is the meaning of life?"
-```
-
-Or install globally:
-```bash
-npm install -g adaptive-memory-multi-model-router
-a3m "Explain quantum computing in simple terms"
-```

package/.github/DISCUSSION_TEMPLATE.yml

@@ -1,5 +0,0 @@
-labels:
-  - show-and-tell
-  - q-a
-  - ideas
-  - announcements

package/.github/FUNDING.yml

@@ -1,2 +0,0 @@
-# These are supported funding model platforms
-github: Das-rebel

package/.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,94 +0,0 @@
----
-name: Bug Report
-about: Report a bug or unexpected behavior to help us improve A3M Router
-title: "[Bug] "
-labels: bug, needs-triage
-assignees: ""
----
-
-## Description
-
-A clear and concise description of the bug.
-
-## Reproduction Steps
-
-Steps to reproduce the behavior:
-
-```bash
-# 1. Set up (if applicable)
-export PROVIDER_API_KEY=sk-...
-
-# 2. Run
-npx a3m-router route "Your query here"
-```
-
-If using the SDK, provide a minimal code snippet:
-
-```typescript
-import { A3MRouter } from "adaptive-memory-multi-model-router";
-
-const router = new A3MRouter({ /* your config */ });
-const result = await router.route("Your query");
-```
-
-## Expected Behavior
-
-What did you expect to happen?
-
-## Actual Behavior
-
-What actually happened? Include error messages, stack traces, or unexpected output.
-
-```
-Paste error output or logs here
-```
-
-## A3M Router Version
-
-- Package: `adaptive-memory-multi-model-router@<version>` (run `npm list adaptive-memory-multi-model-router`)
-- CLI version (if applicable): `npx a3m-router --version`
-
-## Environment
-
-- **OS:** macOS / Linux / Windows
-- **Node.js version:** (run `node --version`)
-- **npm version:** (run `npm --version`)
-- **Python version (if using Python SDK):** (run `python --version`)
-
-## Providers Used
-
-Which provider(s) were involved? (e.g., Groq, OpenAI, Anthropic, NVIDIA, DeepSeek, custom)
-
-## Configuration
-
-Attach or describe relevant config (redact API keys):
-
-```json
-{
-  "providers": { ... },
-  "routing": { ... },
-  "budgets": { ... }
-}
-```
-
-## Logs
-
-If you ran with `DEBUG=*` or `LOG_LEVEL=debug`, include relevant log lines:
-
-```
-[DEBUG] Routing query...
-[ERROR] Provider groq returned 503
-```
-
-## Additional Context
-
-- Does this happen consistently or intermittently?
-- Does it affect all providers or a specific one?
-- Did it work in a previous version? If so, which version?
-- Any recent changes to your setup?
-
-## Checklist
-
-- [ ] I have searched existing issues for duplicates
-- [ ] I have redacted all API keys and secrets from the above
-- [ ] I can reliably reproduce this bug

package/.github/ISSUE_TEMPLATE/config.yml

@@ -1,17 +0,0 @@
-blank_issues_enabled: false
-contact_links:
-  - name: "\U0001F4D6 Documentation & Quick Start"
-    url: https://github.com/Das-rebel/a3m-router#readme
-    about: Check the README for setup, SDK usage, API reference, and configuration examples
-  - name: "\U0001F4AC Discussions & Community"
-    url: https://github.com/Das-rebel/a3m-router/discussions
-    about: Ask questions, share ideas, show what you've built, and get help from the community
-  - name: "\U0001F680 NPM Package"
-    url: https://www.npmjs.com/package/adaptive-memory-multi-model-router
-    about: View package details, version history, and download statistics
-  - name: "\U0001F4DC Changelog"
-    url: https://github.com/Das-rebel/a3m-router/blob/main/CHANGELOG.md
-    about: See what's changed in recent releases
-  - name: "\U0001F6A8 Security"
-    url: https://github.com/Das-rebel/a3m-router/security/policy
-    about: Report security vulnerabilities privately

package/.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,71 +0,0 @@
----
-name: Feature Request
-about: Suggest an idea or enhancement for A3M Router
-title: "[Feature] "
-labels: enhancement
-assignees: ""
----
-
-## Problem Statement
-
-A clear description of the problem you're trying to solve. What gap or pain point does this feature address?
-
-**Example:** "Currently, A3M Router doesn't support routing based on response language. When I send multilingual queries, I want them routed to providers that perform best in that language."
-
-## Proposed Solution
-
-Describe the feature you'd like to see. Be as specific as possible about behavior, configuration, and API.
-
-```typescript
-// If applicable, sketch the API you envision
-const router = new A3MRouter({
-  languageRouting: {
-    enabled: true,
-    defaultProvider: "openai",
-    languageOverrides: {
-      ja: "anthropic",
-      zh: "deepseek",
-    },
-  },
-});
-```
-
-## Use Case
-
-Describe the real-world scenario that would benefit from this feature.
-
-- Who is the target user? (e.g., solo developer, enterprise team, researcher)
-- What workflow does it enable or simplify?
-- How frequently would this be used?
-
-## Alternatives Considered
-
-List any workarounds or alternative approaches you've explored:
-
-1. Manual provider selection per query
-2. Custom wrapper script
-3. Forking and modifying the router
-4. Using a different tool altogether
-
-Explain why these are insufficient.
-
-## Priority
-
-How important is this to you?
-
-- [ ] **Blocking** — Cannot proceed without this feature
-- [ ] **High** — Important for my workflow
-- [ ] **Medium** — Nice to have
-- [ ] **Low** — Interesting idea, not urgent
-
-## Would You Implement It?
-
-- [ ] **Yes** — I can submit a PR (with guidance)
-- [ ] **Maybe** — Willing to help test or provide requirements
-- [ ] **No** — Just suggesting
-
-## Additional Context
-
-- Links to related discussions, issues, or external references
-- Screenshots or mockups (if applicable)
-- Any constraints or requirements (e.g., must work offline, must not increase bundle size)

package/.github/PULL_REQUEST_TEMPLATE.md

@@ -1,71 +0,0 @@
-## Description
-
-Please include a summary of the change and which issue it fixes. Explain the motivation and context — what problem does this solve and why is this the right approach?
-
-Fixes # (issue)
-
-## Type of Change
-
-Check all that apply:
-
-- [ ] 🐛 **Bug fix** (non-breaking change that fixes an issue)
-- [ ] ✨ **New feature** (non-breaking change that adds functionality)
-- [ ] 💥 **Breaking change** (fix or feature that would break existing functionality)
-- [ ] 📚 **Documentation** (README, API docs, inline comments, or examples)
-- [ ] 🎨 **Style** (formatting, code style — no logic change)
-- [ ] ⚡ **Performance** (improves speed, memory, or latency without behavior change)
-- [ ] 🔒 **Security** (fixes a vulnerability or improves security posture)
-- [ ] ♻️ **Refactor** (code change that neither fixes a bug nor adds a feature)
-- [ ] 🧪 **Tests** (adds or updates tests, not production code)
-
-## Testing
-
-Describe the tests you ran to verify your changes:
-
-- [ ] All existing tests pass (`npm test`)
-- [ ] Added new tests for the changes
-- [ ] Tested manually (describe the commands or SDK calls used)
-- [ ] Tested with real provider API calls (if applicable)
-
-```bash
-# Provide commands to reproduce your testing
-node test/some-test.js
-npx a3m-router route "Test query"
-```
-
-## Checklist
-
-- [ ] My code follows the project's coding style and conventions
-- [ ] I have performed a self-review of my own code
-- [ ] I have commented complex logic, especially in hard-to-understand areas
-- [ ] I have updated the documentation (README, API docs, JSDoc comments) if needed
-- [ ] My changes produce no new warnings (no `console.log` left behind, no TypeScript errors)
-- [ ] I have added tests that prove my fix is effective or my feature works
-- [ ] New and existing unit tests pass locally
-- [ ] Any dependent changes are merged and published in downstream modules
-- [ ] I have checked that my changes are backward-compatible (or documented breaking changes)
-
-## Screenshots (if applicable)
-
-If the change affects the terminal UI, dashboard, or any visual output, include screenshots:
-
-| Before | After |
-|--------|-------|
-| _screenshot_ | _screenshot_ |
-
-## Additional Context
-
-- Related issues or PRs
-- Performance impact (latency, memory, bundle size)
-- Configuration changes required
-- Migration guide (if breaking change)
-
-## Changelog Entry
-
-Suggest a one-line changelog entry for this change:
-
-```
-- {type}: {short description} ({issue/PR link})
-```
-
-Example: `- feat: add language-based routing override (#42)`

package/.github/dependabot.yml

@@ -1,9 +0,0 @@
-version: 2
-updates:
-  - package-ecosystem: "npm"
-    directory: "/"
-    schedule:
-      interval: "weekly"
-    open-pull-requests-limit: 10
-    labels:
-      - "dependencies"

package/.github/workflows/auto-publish.yml

@@ -1,51 +0,0 @@
-name: Auto-Publish (7x daily)
-
-# Keeps package on npm "recently updated" feed
-# Each publish drives ~137 organic downloads
-# Schedule: every 3.4 hours = 7x daily
-
-on:
-  schedule:
-    - cron: '0 0,3,7,10,14,17,21 * * *'  # 7x daily UTC
-  workflow_dispatch:  # manual trigger
-
-jobs:
-  publish:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: write
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          fetch-depth: 0  # Fetch full history for version tracking
-
-      - uses: actions/setup-node@v4
-        with:
-          node-version: 20
-          registry-url: 'https://registry.npmjs.org'
-
-      - run: npm ci
-
-      - name: Build
-        run: npm run build
-
-      - name: Get current version
-        id: version
-        run: echo "VERSION=$(node -p "require('./package.json').version")" >> $GITHUB_OUTPUT
-
-      - name: Add research insight
-        run: |
-          echo "## $(date -u +%Y-%m-%dT%H:%MZ)" >> research/PUBLISH_LOG.md
-          VER=$(node -p "require('./package.json').version")
-          echo "Published v$VER" >> research/PUBLISH_LOG.md
-          echo "" >> research/PUBLISH_LOG.md
-
-      - name: Patch + Publish + Commit
-        run: |
-          npm version patch --no-git-tag-version
-          npm publish
-          git add -A
-          git commit -m "chore: auto-publish v$(node -p "require('./package.json').version")" || echo "Nothing to commit"
-          git push || echo "Push failed (upstream may have changes)"
-        env:
-          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}