AgentLedger
PulseGate's liveness check found it on 14 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 16 Jun 2026. How this is checked
AgentLedger is an open-source observability and control tool for AI agents. It is built for monitoring what agents actually do, with a focus on actions, costs, and stopping agents when things go wrong. The page frames it around agents that send emails, create tickets, charge credit cards, and call APIs.
Inferred · not functionally tested
Overview
6 featuresPurpose: Monitoring, controlling, and ensuring the safety and cost-effectiveness of autonomous AI agents in production environments.
Inferred · not functionally tested
Audience: AI developers and teams deploying agentic systems
Inferred · not functionally tested
Functions: monitoring, analytics, agents
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: unknown
Recorded constraints: pricing: open_source · license: MIT · platforms: CLI, WEB · deployment: browser, cli, cloud_managed, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: agentledger.co · github.com. These links do not verify the individual claims.
In the Agent monitoring & governance space, AgentLedger takes a focused approach. Inferred · not functionally tested: Monitoring, controlling, and ensuring the safety and cost-effectiveness of autonomous AI agents in production environments. Inferred · not functionally tested: It is built as an open-source project for AI developers and teams deploying agentic systems. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: AgentLedger is available on the web, the command line, and API.
AgentLedger first shipped in 2026. Inferred · not functionally tested: Key capabilities include action logging, cost tracking, and safety controls. Inferred · not functionally tested: Catalogued interfaces include an MCP server and a public API.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Action logging
- Cost tracking
- Safety controls
- Budget management
- Kill switches
- Anomaly detection
Topics: Inferred · not functionally tested
Built with & integrations
- Next.js
- x-nextjs-prerender header · /_next/static/ in the HTML · __next_f in the HTML
- Vercel
- x-vercel-id header · x-vercel-cache header
- multiple
- bLangChain in the HTML · bLlamaIndex in the HTML
Trust & compliance
Indexing history
What PulseGate has recorded for this listing
Frequently asked questions about AgentLedger
- What does AgentLedger do?
- Inferred · not functionally tested: Monitoring, controlling, and ensuring the safety and cost-effectiveness of autonomous AI agents in production environments. It is catalogued under Agent monitoring & governance on PulseGate.
- Who should use AgentLedger?
- Inferred · not functionally tested: AgentLedger is an open-source project built for AI developers and teams deploying agentic systems.
- Is AgentLedger free?
- Basis unknown · not verified: Yes — AgentLedger is open source under the MIT license and free to use.
- What platforms does AgentLedger run on?
- Basis unknown · not verified: AgentLedger runs on the web, the command line, and API.
- Is AgentLedger still active?
- PulseGate's liveness check found it on 14 Sep 2026.
- What are alternatives to AgentLedger?
- Similar projects tracked by PulseGate include AI Agent City, AgenticLedger, and ai-agent-ledger-py.AI Agent CityAgenticLedgerai-agent-ledger-py
- When did AgentLedger launch?
- AgentLedger first shipped in 2026.
- Is AgentLedger open source?
- Basis unknown · not verified: Yes — AgentLedger is open source under the MIT license, developed on GitHub.
Similar projects
Closest matches by what these projects do