Google PageRank for AI agents. 25,000+ tools indexed.

prism-coder MCP Server

dcostenco/prism-coder

Score: 89.9 → 0% Rank #358 Database
[![AgentRank](https://agentrank-ai.com/api/v1/badge/dcostenco--prism-coder)](https://agentrank-ai.com/tool/dcostenco--prism-coder/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Are you the maintainer of dcostenco/prism-coder? Claim this listing →

Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.

Add AgentRank to Claude Code Discover and compare tools like dcostenco/prism-coder — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

dcostenco/prism-coder is a TypeScript tool licensed under Apache-2.0. Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex. Topics: agent-memory, mcp, mcp-server, model-context-protocol, typescript, ai-agent, semantic-search, local-first, sqlite, vector-search, cognitive-architecture, local-llm, ollama, prism-coder, claude-code, codex, drift-detection, memory, session-memory.

Ranked #358 out of 24846 indexed tools.

In the top 2% of all indexed tools.

Actively maintained with commits in the last week.

Ecosystem

TypeScript Apache-2.0 1,474 npm/wk
agent-memorymcpmcp-servermodel-context-protocoltypescriptai-agentsemantic-searchlocal-firstsqlitevector-searchcognitive-architecturelocal-llmollamaprism-coderclaude-codecodexdrift-detectionmemorysession-memory

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 158

158 stars → growing community

Freshness 25% 4d ago

Last commit 4d ago → actively maintained

Issue Health 25% 100%

38/38 issues closed → responsive maintainer

Contributors 10% 7

7 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads 13% 1,474/wk

1,474 weekly installs → gaining traction

PyPI Downloads N/A
Forks 26
Description Detailed
License Apache-2.0

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

Badge all embed codes →

AgentRank score for dcostenco/prism-coder
[![AgentRank](https://agentrank-ai.com/api/v1/badge/dcostenco--prism-coder)](https://agentrank-ai.com/tool/dcostenco--prism-coder/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/dcostenco--prism-coder/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/dcostenco--prism-coder" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="dcostenco/prism-coder"></script>

Matched Queries

topic:mcptopic:mcp-servertopic:model-context-protocol

From the README

# Prism Coder

**Give your AI agent memory that lasts — and see the cloud tokens it never had to spend.** Persistent sessions, knowledge graphs, offline tool-routing, and an auditable savings meter. Fully local and free.

<p align="center">
  
</p>

Prism Coder is an [MCP server](https://modelcontextprotocol.io) that gives Claude, Cursor, and other AI tools long-term memory that survives across sessions. It ships with the open-weight `prism-coder` model fleet (2B–27B) for fast, offline tool-routing — no cloud required. And it keeps score: every call served locally is metered, so `prism savings` shows the token volume that never reached your cloud model — [measured honestly, in tokens](#local_savings--what-local-serving-actually-displaced).

**No account needed. No API keys. Runs on your machine.**  
A paid subscription adds cloud sync, higher model tiers, and team features through the [Synalux portal](https://synalux.ai).

---

## What Prism gives you

- **Session memory that survives 
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.