See what your AI coding agents did, and what it cost.

AgentsView brings your AI coding sessions into one searchable archive. Browse recorded conversations from more than 60 agent formats, compare activity and costs, and reuse lessons from past work. The archive stays on your machine unless you turn on a feature that shares it.

curl -fsSL https://agentsview.io/install.sh | bash

New in v0.45.0: Spanish, Junie/OMO/StepCode sessions, tool sequences, and conversation-memory plugins.

macOS and Linux · Windows, desktop app, pip, and Docker installs

See how it works Read the docs

AgentsView dashboard summarizing sessions, cost, and activity across agents

Local-first · MIT · Single Go binary · Desktop · Web · CLI · MCP · SQLite / PostgreSQL / DuckDB / ClickHouse

01 / Record

Your coding sessions, in one archive.

A background server watches the session directories your agents already write and imports supported formats into a local SQLite archive. It finds the default directories automatically. You can configure other locations. Start a session in one window and watch it stream into AgentsView in another.

Claude Code OpenClaude ACAugure Code ADAugure Desktop CBCodeBuddy CN Codex Gemini Copilot Cursor Cursor IDE Windsurf VS Code Copilot Visual Studio Copilot Qwen Code DeepSeek TUI DeepSeek Harness Mistral Vibe Zed Warp Amp (historical) OpenCode Positron Posit Assistant Claude Cowork Aider Antigravity gptme Kilo Kilo (legacy) Kimi Kimi Work Omnigent Kiro OpenHands ZCode Zencoder Command Code Cline CLI Codebuff Cortex Code Crush Devin CLI Evener Forge Freebuff Goose Grok Hermes iFlow JuJunie OmOMO StStepCode IcIcodeMate MiMoCode OhMyPi OpenClaw Open Code Review Pi Prime Agent Piebald Poolside QClaw Qoder QwenPaw Reasonix RooCode Shelley Tau Trae TraeX WorkBuddy

60+agent formats parsed

1binary, zero accounts

SQLitearchive of record

02 / Observe

See when your agents are actually working.

The Activity dashboard shows peak concurrency and the exact moment it happened, active versus idle time, agent-minutes across parallel sessions, and cost. Scope it to any day, week, month, or custom range, and filter by project, agent, and machine. Switch from concurrency to user-message or assistant-message frequency to compare prompts and output. The Analytics dashboard adds message-role comparisons and Git outcome totals.

AgentsView Activity dashboard showing concurrency timeline, active time, and cost — The Activity dashboard. Select the image to inspect it at full size. Activity reference.

03 / Account

Know what every agent costs.

Token and cost reports read from the pre-indexed archive instead of reparsing raw session files every time. Pricing tracks LiteLLM and OpenRouter rates with an offline fallback, and cache-aware accounting covers prompt-cache creation and reads. Compare Total Input with Uncached Input, and choose Smooth, Lines, or Bars for the daily cost chart.

AgentsView usage dashboard with daily cost and token breakdowns — Daily spend by agent, model, and project. Token usage reference.

$ agentsview usage daily
last 30 days by agent, model, and project
$ agentsview usage statusline
$9.61 today
$ agentsview capture run -- claude -p "fix the tests"
exact usage for one non-interactive run

04 / Understand

Search and score every transcript.

Find a conversation by project and date in the command palette, or open it by ID with Ctrl/Cmd+G. Full-text search matches words; opt-in semantic and hybrid search match by meaning. Health scores and quality signals link back to the transcript so you can check the evidence. Tool sequences follow errors, retries, switches, and recovery through the recorded calls without running a model.

AgentsView command palette with project and date filters — Choose a project and date range without changing the sidebar. Search controls · Semantic search · Session intelligence · Quality signals.

05 / Remember

Turn transcripts into durable knowledge.

Recall (experimental) extracts decisions, warnings, and project facts from your archive. Each entry links to the messages that support it. Approve useful entries or archive rejected ones; your decisions survive later extraction changes. Generated Insights write model-authored reports over an explicit session scope.

AgentsView Recall corpus browser with extraction coverage and evidence links — The Recall corpus browser. Recall reference.

06 / Feed back

Your agents can read it too.

The same archive is available to your agents through a CLI, a REST API, and an MCP server. An agent can check what a previous session already tried, quote its own history, or watch its spend mid-run. Native conversation-memory plugins bundle recall instructions and session-start refresh for Claude Code and Codex. See memory setup.

CLIScriptable reports and session queries.
RESTProgrammatic session and usage access.
MCPSession history as assistant tools.
SSELive message streams as sessions run.
WebEmbedded Svelte UI in the binary.
DesktopNative app sharing the same data.

Connect over MCP Use the session API

$ agentsview daemon start
daemon watching session directories
$ agentsview session search "flaky websocket test" --hybrid
3 matches with cited conversation units
$ agentsview session usage 51adf --format json
{"cost":{"microdollars":2410000},...}

07 / Share

SQLite is the local archive of record. From there, push parsed sessions to PostgreSQL or ClickHouse, mirror into DuckDB, read provider files from S3, or keep original source files in hosted storage.

PostgreSQL

Push to a shared backend.

An installable auto-push service mirrors each machine's archive into PostgreSQL; a read-only server presents the merged fleet. PostgreSQL sync.

DuckDB / ClickHouse

Choose a reporting backend.

Mirror into DuckDB for local or Quack reads, or push to ClickHouse and serve the dashboard there, including semantic and hybrid search when embeddings are pushed. Keep session edits in SQLite.

Filesystem

Sync without a server.

Point a primary viewer at out-of-band copies of native session directories, including S3-backed sources. Filesystem sync.

Hosted raw sync

Keep the original files off-device.

Upload original session files to an operator-managed server with device credentials and resumable transfers. Opt-in server parsing makes those sessions browsable in PostgreSQL without a local SQLite archive or a separate pg push. Hosted raw sync.

Remote access

Reach it from anywhere you trust.

Loopback by default, with explicit flags for SSH forwards, remote dev environments, and authenticated non-loopback exposure. Remote access.

Artifact folders

Exchange normalized revisions.

Move immutable session revisions between trusted folders for experimental portable workflows. Artifact folder sync.

08 / Own

Local by default. Shared when you choose.

Your agent transcripts can contain source code, credentials, paths, and private conversations. AgentsView starts with one local SQLite archive and a loopback-only server. Session content leaves the machine only through features you choose.

Default

Keep the archive on your machine.

Browse, search, report, and run local Recall workflows without sending session content to an AgentsView account.

Your choice

Share only for a clear purpose.

Configure PostgreSQL, ClickHouse, remote DuckDB, Generated Insights, GitHub publishing, or hosted raw sync only when that outcome is worth sending data.

Visible boundaries

Know what crosses the boundary.

Each sharing feature documents what it sends, where it goes, and which controls apply. Privacy details.

09 / Start

Your agents are already writing the data.

Install AgentsView and it finds the sessions that are already on your machine. The guide walks the whole loop in five minutes; the docs cover installation, workflows, and exact command behavior.

Follow the guide Run the quickstart