AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Observability/
bar-observatory
bar-observatory logo

bar-observatory

Active·★ 24·MIT·Updated 2026-08-27

BAR Observatory is an open-source, local-only audit tool for Claude Code sessions, acting as a flight recorder to capture and report every agent action. It provides deterministic reports in JSON, HTML, and Markdown, enabling verification of agent performance without relying on its self-summary or external services.

#Agentic AI#LLM Observability#Audit Tool#Session Analysis#Deterministic Reports#Claude Code#Local-only#Rust
$ Install
$ cargo install bar-hook bar-mcp bar-observatory
↗ Visit site★ GitHub
01

Features

01Capture and report every agent tool call, task, and sub-agent dispatch.
02Generate deterministic reports in JSON, HTML, and Markdown, without an LLM in the render path.
03Identify and surface all errors and rework hotspots from agent sessions.
04Operate locally with zero network egress for the primary path, ensuring data privacy.
02

Compatibility

Rust
Language
Verified via docs
Claude Code
Integration
Verified via docs
Windows
OS
Verified via docs
MacOS
OS
Verified via docs
Linux
OS
Verified via docs
03

Quick start

1
$ cargo install bar-hook bar-mcp bar-observatory
04

Use cases

↳Audit and verify what an AI agent actually did in a session, beyond its self-summary.
↳Provide a reproducible artifact (e.g., for PRs, reviews, compliance) of AI-assisted work.
↳Debug multi-agent runs by surfacing hidden failures and rework efforts.
↳Enable AI agents to audit their own past sessions for self-improvement loops.
05

Alternatives

⚡Top VS:
VSpreflight★65→VSyavio★31→VSagentgateway★5.5k→VScodex-usage-tracker★196→
preflight logo
preflight★ 65
Observability for AI coding assistants — cost tracking, efficiency scoring, and anti-pattern detection for Claude Code, Cursor, Copilot, and more. Local-first; New Relic optional.
VSCompare→
yavio logo
yavio★ 31
The Open Source Analytics and Visibility Layer for ChatGPT Apps and MCP Apps.
VSCompare→
agentgateway logo
agentgateway★ 5.5k
Next Generation Agentic Proxy for AI Agents and MCP servers
VSCompare→
codex-usage-tracker logo
codex-usage-tracker★ 196
Local-first MCP tools and dashboard for investigating Codex token usage, credits, costs, caching, and thread patterns.
VSCompare→
metorial-platform logo
metorial-platform★ 221
The engine powering hundreds of thousands of MCP connections 🤖 🔥
VSCompare→
Awesome-LLM-in-Social-Science logo
Awesome-LLM-in-Social-Science★ 652
Awesome papers involving LLMs in Social Science.
VSCompare→
agentsilex logo
agentsilex★ 458
A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.
VSCompare→
palico-ai logo
palico-ai★ 343
Build, Improve Performance, and Productionize your LLM Application with an Integrated Framework
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
bar181 /
bar-observatory
↗

Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

24MIT
Last commit1mo ago
StatusActive
CategoryObservability
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.