velocity

Velocity is a local-first web app (Next.js + Bun) that acts as a command center for AI coding CLIs (Claude Code, Codex CLI, Gemini CLI). It runs and inspects coding sessions, captures analytics (usage/cost/latency/tools/routing context), and helps turn repeated patterns into reusable agents/workflows/skills/commands, including routing visualization. It also supports MCP (via the @modelcontextprotocol/sdk dependency) as part of its build layer surfaces.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ DevTools ai-ml local-first developer-tools workflow-automation session-analytics model-context-protocol nextjs bun sqlite
⚙ Agent Friendliness
40
/ 100
Can an agent use this?
🔒 Security
35
/ 100
Is it safe for agents?
⚡ Reliability
25
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
35
Documentation
45
Error Messages
0
Auth Simplicity
90
Rate Limits
0

🔒 Security

TLS Enforcement
50
Auth Strength
20
Scope Granularity
0
Dep. Hygiene
55
Secret Handling
60

Security section is high-level: “local-first” and optional remote calls limited to explicit user-driven actions. The README does not describe web authentication/authorization, TLS requirements for the local server, secret storage/handling, or threat model details. Dependency hygiene is uncertain from the provided data (not assessed for CVEs here). Local SQLite storage suggests data-at-rest on device, but the documentation provided is insufficient to confirm encryption at rest or secure logging.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
0
Error Recovery
55
AF Security Reliability

Best When

You want local, inspectable AI-agent session history and a workflow builder/routing analytics layer around existing model CLIs on your own machine.

Avoid When

You require a fully specified public API contract (REST/GraphQL/OpenAPI) for programmatic integration, or you need explicit enterprise-grade auth/compliance details from documentation.

Use Cases

  • Run CLI-based AI coding sessions in a local workspace
  • Review session transcripts with usage/latency/cost/tool/routing context
  • Convert repeated agentic patterns into reusable workflows/skills/commands
  • Visualize routing graphs to debug and improve automation
  • Build and manage “agents” and “workflows” across Claude/Codex/Gemini with provider parity

Not For

  • As a hosted SaaS for team-wide collaboration without local deployment needs
  • As a standalone third-party REST API service consumed by external systems (it’s primarily an app/UI)
  • Environments requiring strong documented security guarantees beyond local-first defaults (README provides limited specifics)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
Yes
Webhooks
No

Authentication

Methods: Local usage (no auth described for accessing the app)
OAuth: No Scopes: No

README describes local-first data handling but does not document any authentication mechanism for the web UI/API endpoints. Provider credentials for Claude/Codex/Gemini are not specified in the provided README content.

Pricing

Free tier: No
Requires CC: No

Self-hosted open-source (AGPL-3.0) based on README; no hosted pricing model described.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • This appears to be a local web app rather than a clear programmatic API; an agent may need browser/UI automation or direct internal module usage unless an external API is documented elsewhere.
  • PTY/node-pty setup issues on macOS can block session execution (README provides a chmod workaround), which may impact agent workflows if not handled.
  • The README lists MCP as a surface area but provides no concrete MCP server URL or tool schema in the provided content, so automated tool invocation may be unclear without further docs.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for velocity.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered