whereismyai
AgentsView
AgentsView is an open source local-first session archive tool that records, searches, and tracks costs for AI coding agents.
AgentsView brings your AI coding sessions into one searchable archive. A background server watches session directories, imports formats from more than 60 agent types, and stores them locally in SQLite. The platform provides activity dashboards, token and cost reports, command palette search, and semantic transcript scoring. It is designed for developers who use AI coding agents and need to track usage, costs, and past decisions. The architecture supports local-first privacy with optional sync options including PostgreSQL, DuckDB, and ClickHouse.
AgentsView at a glance
- Best for: Software engineer
- Runs on: Web, macOS, Windows, Linux, CLI, API, self-hosted, open source
- Pricing: Free and open source under the MIT license
- Released: February 2026
- Category: AI coding tool
- Website: agentsview.io
Key features
- Background server imports agent session directories
- Activity dashboard tracks concurrency and active time
- Token and cost reports track LiteLLM and OpenRouter rates
- Full-text, semantic, and hybrid search across transcripts
- Recall extracts decisions and warnings from archives
- CLI, REST API, and MCP server access for agents
- Local SQLite archive with optional PostgreSQL or ClickHouse sync
Use it for
- Browse recorded AI coding sessions and search past work
- Track exact costs and token usage for coding agents
- Search transcripts to find previous code attempts
- Sync session archives to shared PostgreSQL backends
Companions
Tools that articles about AgentsView recommend using with it, each with its job.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Ollama — Run local models at zero marginal cost, with code kept on your machine.
- OpenRouter — Access over 500 models and 80 providers through one unified API.
- Daytona — Runs sessions in isolated sandboxes synced to git branches.
- Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
- Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.
Alternatives to AgentsView
- Alook — Connects existing local coding agents to team communication channels.
- AgentOps — Track token usage, costs, and traces across 400 plus LLMs and agent frameworks.
- Agent Archive — Hand off coding sessions between Claude Code, Codex, and Cursor across machines.
- OpenCode — Works with 75+ model providers, local models, and existing subscriptions
- Mindwalk — Visualize how coding agents explore and edit files on a 3D repository map.
- AGENTS.md — It separates agent-specific instructions from human-focused README files.
- Opaline — Track team-wide token costs and coding session analytics.
- AgentScope — Offers triple-layer security with sandboxing and tool reviews.
- Agent Beacon — Retains coding agent knowledge across tools so errors do not repeat.
- AI Memory — Shared memory for coding agents that works across machines and team members.
- Entelligence AI — Inspect agent sessions locally without digging through logs or sharing data.
- Agent OS — Manage AI coding sessions side by side and check on them from your phone.
All AgentsView alternatives