Agentmemory vs Voyage AI

Side-by-side comparison of features, pricing, and ratings

Live tool data as of 2026-07-17
Reviewed by our team on
Saved

At a glance

DimensionAgentmemoryVoyage AI
Pricingfreecontact
Best forDevelopers using Claude Code who need persistent memory across sessions, Teams working on large codebases where agents lose contextEnterprise RAG pipelines needing high-accuracy retrieval on finance or legal documents, Teams requiring long-context embeddings (32K tokens) for thorough document understanding
Standout features12 auto-capture hooks for agent tool calls, prompts, stops · Triple-stream retrieval: BM25 + vector + knowledge graph · On-device reranker achieving 95.2% R@5 recall on LongMemEval-SEmbedding models: voyage-3.5 and voyage-3.5 lite · Domain-specific models for finance, legal, and code · Company-specific fine-tuned models
Viability score87/10075/100
APIYesYes

Agentmemory is the stronger pick for developers using claude code who need persistent memory across sessions; Voyage AI fits better for enterprise rag pipelines needing high-accuracy retrieval on finance or legal documents.

Built from live tool data, last verified 2026-07-17.

Agentmemory
Agentmemory

Open-source persistent memory runtime for AI coding agents with 95.2% recall

Visit Website
Voyage AI
Voyage AI

Domain-specialized embedding models and rerankers for enterprise RAG.

Visit Website
Pricing
Free
Contact Sales
Plans
Free
Popularity
1 views
7.4k views
Skill Level
Intermediate
Intermediate
API Available
Platforms
CLIPluginAPI
API
Categories
💻 Code & Development⚙️ Developer Infrastructure
⚙️ Developer Infrastructure
Features
12 auto-capture hooks for agent tool calls, prompts, stops
Triple-stream retrieval: BM25 + vector + knowledge graph
On-device reranker achieving 95.2% R@5 recall on LongMemEval-S
~92% token reduction vs full-context approaches
Hourly consolidation: compress, merge duplicates, decay stale
53 MCP tools for memory operations
128 REST endpoints mirroring MCP surface
Graph extraction and knowledge graph visualization
Mesh federation: peer-to-peer sync over authenticated HTTPS
Markdown Obsidian export with frontmatter tags
OTEL observability with spans and logs (Jaeger, Honeycomb, Tempo)
JSONL session import from Claude Code transcripts
Supports 5 LLM providers (Claude, Anthropic, Gemini, MiniMax, OpenRouter)
Zero external databases: runs on local SQLite/JSON
Real-time viewer on port 3113 and engine console on port 3114
Embedding models: voyage-3.5 and voyage-3.5 lite
Domain-specific models for finance, legal, and code
Company-specific fine-tuned models
Voyage 4 model series (newly announced)
Multimodal model: voyage-multimodal-3.5
Long-context support up to 32K tokens
Low-dimensional embeddings (3x-8x shorter vectors)
Reranker models: rerank-2.5 and rerank-2.5-lite
Instruction following for reranker models
Batch API for large-scale workloads
Voyage-context-3: chunk-level details with global context
Low-latency inference (4x smaller model)
SOC 2 and HIPAA compliance
Modular: works with any vector DB and LLM
Integrations
Claude Code
Cursor
GitHub Copilot
Codex CLI
Gemini CLI
Cline
OpenRouter
Anthropic API
Gemini
MiniMax
Obsidian
Jaeger
Honeycomb
Tempo
OpenClaw

Who should pick which

  • Solo developer using Claude Code
    Pick: Agentmemory

    Free, easy self-hosted setup, and directly integrates with Claude Code via MCP hooks. Eliminates context loss across sessions.

  • Enterprise RAG team in finance
    Pick: Voyage AI

    Voyage's finance-specific embedding model, long 32K context, and low-dimensional vectors optimize accuracy and cost for financial document retrieval.

  • Open-source contributor team
    Pick: Agentmemory

    Open-source, self-hosted, with mesh federation for team sync. No vendor lock-in, community-driven development.

  • Legal tech startup building document review
    Pick: Voyage AI

    Legal domain model and high recall from rerankers improve accuracy in legal document retrieval, despite higher cost.

  • AI agent memory researcher
    Pick: Agentmemory

    Supports graph extraction, Obsidian export, and OTEL observability — ideal for experimenting with memory architectures. Free and extensible.

Frequently Asked Questions

Which is better, Agentmemory or Voyage AI?

The best choice between Agentmemory and Voyage AI depends on your specific use case — we compare them independently on features, current pricing, integrations, and real-world signals (with an on-demand sentiment scan available for each). See the side-by-side breakdown above to match them to your needs.

What are the main differences between Agentmemory and Voyage AI?

The key differences include pricing model, feature set, platform support, and skill level requirements. Review the full comparison on RightAIChoice for a detailed breakdown.

Is there a free version of Agentmemory or Voyage AI?

Check the pricing section in the comparison for the latest pricing details on both tools, including free tiers, trial options, and paid plans.

More Agentmemory or Voyage AI comparisons

Explore each tool further

Browse these categories

Still deciding? Get the weekly AI tools brief

One email a week — new tools, honest comparisons, no spam.