AgentsView Session Archive

Search coding-agent sessions locally and inspect token use, estimated costs, and activity.

Stars
★ 6.5k
Last updated
today
License
MIT
Primary language
Go

At a glance

How it runs
CLIWeb appDesktop app
Works with
Universal · cross-platformCodex · Claude Code
Cost
Free, no paid service needed
Setup effort
Low · running in minutes
You'll need
Go 1.27+ (CGO)Node.js 24.11+DockerGitHub CLIShell / CLINetwork accessLocal filesystem
Typical use
A developer using Claude Code, Codex, and other tools wants one local interface to search and revisit sessions.
Not a fit if
  • Developers who need session browsing inside their IDE
  • Teams that need Cursor attribution stats synced to PostgreSQL
Website
agentsview.io ↗ set on GitHub
Maintenance
Commits in the last 30 dayslast commit 2026-11-21latest release v0.47.0 (2026-11-09)+7.9 ★/day over 7 days
Source review
76/100 · Good

What does this agent do, and when should you use it?

AgentsView is a local-first session browser and analytics tool for coding agents, with a Go CLI, a Go-served web UI, and desktop apps for macOS and Windows. On first run it discovers sessions from supported agent directories, syncs them into a local SQLite archive, and serves the UI at 127.0.0.1:8080 by default. The CLI lists and searches sessions, reports token use and estimated costs, and emits windowed statistics; the UI provides full-text search, session viewing, cost dashboards, and activity analytics. Optional PostgreSQL, ClickHouse, and DuckDB targets can receive pushed or mirrored archive data and serve it read-only. Session content stays local by default; telemetry can be disabled, while semantic search, GitHub Gist export, and remote sync involve their configured external services.

AgentsView reads local session files from Claude Code, Codex, and other supported tools, parses them, and stores sessions and messages in SQLite. agentsview serve starts the server, web UI, sync, and file watchers; agentsview daemon start runs it in the background. Commands such as agentsview session list, agentsview usage daily, and agentsview stats read the archive and return sessions, cost summaries, and analytics. agentsview session search supports full-text search, with semantic or hybrid search available after configuring an embeddings endpoint. The web UI displays transcripts, token use, costs, activity heatmaps, and tool usage; the REST API exposes per-session usage at /api/v1/sessions/{id}/usage. Optional pg push, clickhouse push, and duckdb push copy the SQLite archive to those destinations for read-only serving or analysis.

  1. A developer using Claude Code, Codex, and other tools wants one local interface to search and revisit sessions.
  2. An individual developer wants daily or per-model token and estimated-cost reports across coding agents.
  3. A team wants to push local archives to PostgreSQL for a shared, read-only dashboard.
  4. An analyst wants a DuckDB mirror or a ClickHouse copy for read-only querying.
  5. A user building automation wants CLI JSON output, stats, or the per-session REST API for scripts.

Key setup facts

Pulled from the install and usage notes below. The project README has the current values.

Install / run
  • curl -fsSL https://agentsview.io/install.sh | bash
  • brew install --cask agentsview
  • docker run --rm -p 127.0.0.1:8080:8080 \
Ports
8080
Environment variables
CLAUDE_PROJECTS_DIR
Install notes cover
Windows · macOS · Linux · Docker

How do you install or deploy this agent?

Install the CLI on macOS or Linux with:

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

On Windows, use PowerShell:

powershell -ExecutionPolicy ByPass -c "irm https://agentsview.io/install.ps1 | iex"

The desktop app is available for macOS and Windows; on macOS, Homebrew is also supported:

brew install --cask agentsview

The Docker image is another documented option. Mount agent session directories and set their matching environment variables so the container can discover those sessions:

docker run --rm -p 127.0.0.1:8080:8080 \
  -v agentsview-data:/data \
  -v "$HOME/.claude/projects:/agents/claude:ro" \
  -e CLAUDE_PROJECTS_DIR=/agents/claude \
  ghcr.io/kenn-io/agentsview:latest

How do you use this agent?

On first run, AgentsView discovers supported session sources, syncs them into SQLite, and starts the local web UI:

agentsview serve

Open http://127.0.0.1:8080 in a browser. Common CLI commands include:

agentsview daemon start
agentsview session list
agentsview usage daily
agentsview stats --format json

Search with agentsview session search; semantic search requires an OpenAI-compatible embeddings endpoint. Per-session usage is available from the CLI or REST API:

agentsview session usage <id>
curl http://127.0.0.1:8080/api/v1/sessions/<id>/usage

Daily usage reports read the saved archive. Run agentsview sync first to include new changes from source directories.

What are this agent's strengths and limitations?

Pros
  • Consolidates local sessions from more than 20 coding agents in SQLite, with FTS5 full-text search and project/date filters.
  • Provides cross-agent usage, cost, and analytics through CLI reports, JSON output, and a per-session REST API.
  • Keeps SQLite as the primary archive while offering PostgreSQL, ClickHouse, and DuckDB as optional push or read-only mirror backends.
  • Offers CLI, web UI, macOS and Windows desktop apps, and Docker deployment.
Limitations
  • Each agent needs an accessible local session directory; Docker deployments must mount directories and set matching environment variables.
  • Semantic search requires an OpenAI-compatible embeddings endpoint; cost estimates depend on available pricing, and some proprietary models may be unpriced.
  • PostgreSQL, ClickHouse, and DuckDB features require extra backend configuration; remote access also requires appropriate authentication, TLS, or a trusted proxy.
  • The README does not specify desktop OS version requirements; source development requires Go 1.27+ (CGO) and Node.js 24.11+.

How does this agent compare with similar options?

The README presents SQLite as the primary archive and PostgreSQL, ClickHouse, and DuckDB as optional shared or mirror backends. SQLite supports writes and FTS5 indexed search; remote backends serve read-only. DuckDB search uses substring or regex fallback, while SQLite FTS5 is the indexed search path.

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
AgentsView Session Archive This agent 76 · Good CLIFree ★ 6.5k today Go Codex · Claude Code
LeanCTX Context Intelligence 69 · Some gaps CLIFree + model costs ★ 4k 5d ago Rust Codex · Claude Code · OpenAI API · Claude API
ccxray 76 · Good CLIFree + model costs ★ 296 4d ago JavaScript Claude Code · Claude API
Agent Deck 74 · Some gaps CLIFree + model costs ★ 1.3k 6d ago Go Codex · Claude Code

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Good
76/ 100 5-point scale 3.8 / 5
This review covers the source as of Nov 08, 2026. The project has shipped 1 stable release(s) since, which have not been re-reviewed. The score and verdict describe the reviewed version only. Recent releases ↓
Trust 19/29
Reliability 9/14
Adaptability 16/18
Convention 14/18
Effectiveness 12/13
Verifiability 6/8
Why each dimension lost points
Trust19 / 29 · 3.3/5

Evidence shows loopback binding by default, read-only session mounts in container examples, authentication guidance for remote access, and selectable full, transcripts, or usage archive policies with clear limits and rebuild consequences. Deductions: the default full policy retains sensitive conversation content, and installation examples pipe downloaded scripts into shells; optional semantic search, cloud sync, and export have user-configured external effects, but the supplied files do not fully describe confirmation steps or each data flow.

Reliability9 / 14 · 3.2/5

The README, Quick Start, and configuration guide are broadly consistent about daemon behavior, archive policies, deployment, and limitations; they describe behaviors such as preserving the active log if rotation fails and SHA-256 verification by the installer. Deducted because network services and optional components are involved without a complete account of failure behavior for each dependency; source excerpts cannot establish runtime correctness.

Adaptability16 / 18 · 4.4/5

The product covers CLI, desktop, containers, CI, forwarded access, multiple platforms, and many session sources. It states that Aider is opt-in, Amp support is deprecated, Codex Cloud is disabled by default, and containers see only mounted sources. Deducted because the supplied skills mainly describe maintenance-task triggers, so they do not establish equally precise end-user capability triggers throughout the product.

Convention14 / 18 · 3.9/5

Documentation is organized around installation, operation, configuration, data policy, and deployment, with detailed commands, platform differences, examples, and limitations; license metadata says MIT. Deducted because the license text and changelog contents are not supplied, only the latest version and a changelog link. Publisher identity is unknown, and repository maintenance instructions do not clearly identify who owns product maintenance or long-term support.

Effectiveness12 / 13 · 4.6/5

The product offers local cross-agent session search, cost reporting, analytics, and multiple output paths; CLI commands, JSON output, a REST API, and screenshots support interactive and scripted use. Deducted because full archiving and some advanced features can add storage or configuration costs, and the supplied material does not quantify resource use enough to assess cost-benefit fully.

Verifiability6 / 8 · 3.8/5

Feature claims are supported across the README, Quick Start, configuration guide, and main entry point; the materials distinguish defaults, optional settings, and stated limitations. Deducted because many implementation details are documented claims that the supplied source excerpts do not independently corroborate, and there is no execution or independent test evidence.

Risks and how to mitigate them
  • The default full archive retains parsed messages, reasoning text, tool metadata, and results. Environments containing sensitive data should choose a narrower policy first; policy changes require restart and rebuild, and discarded content cannot be recovered from the archive.
  • Container and non-loopback access require deliberate session-directory mounts and authentication. Optional features such as semantic search, cloud sync, and Gist publishing may involve external services; review their specific configuration before enabling them.
Evidence confidence: Low Reviewed Nov 08, 2026 Reviewed revision d0db4191a27d New commits since this review; the score may not cover them
See the full review method →
Maintain this project? Add the FARS badge to your README

The badge shows the current review score and verdict and links back to this page. It refreshes about once an hour after a re-review.

FARS

[![FARS review](https://followagents.com/badge/agentsview.svg)](https://followagents.com/en/agents/agentsview)
<a href="https://followagents.com/en/agents/agentsview"><img src="https://followagents.com/badge/agentsview.svg" alt="FARS review"></a>

Recent releases

Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.

  1. v0.47.0
    Release notes excerpt
    New features - Review daily problems in the Friction Log, including corrections, tool errors, and recurring patterns linked to exact messages. Browse dates, download Markdown, or read findings through the CLI and MCP. Enable it with [friction] enabled = true. - Turn Friction Log patterns into Kata issues, link existing issues, or remove links from the page or CLI. Enable hourly automatic filing with [friction.kata] auto_file = true. …
    View on GitHub ↗
  2. v0.46.1
    Release notes excerpt
    Improvements - Antigravity CLI sessions show plaintext transcripts with model and token usage attached to the matching model replies. Bug fixes - Antigravity sessions parse again on read-only mounts, including read-only Docker volumes. - Archived Antigravity CLI replies stay intact when the session database cannot be read. - Repeated prompts remain separate turns in Antigravity CLI sessions. Existing archives are reprocessed to recover missing turns. - Docker builds no longer fail because a required Claude.ai Chrome extension file is missing.
    View on GitHub ↗
  3. v0.46.0
    Release notes excerpt
    New features - Sync Claude.ai chats through Chrome, including Google sign-in. Run agentsview chrome setup, load the printed extension folder at chrome://extensions, and restart AgentsView before using Import > Claude.ai. - Import ChatGPT dot, Codex web, and Codex cloud task chats as searchable sessions with the opt-in codex-cloud source. Chats without token counts show OpenAI's plan usage figures. Configure this source on one machine only. …
    View on GitHub ↗

FAQ

Do I need a paid model or API key to use AgentsView?
Local browsing, statistics, and cost reports use the local archive and do not require a model API key. Semantic search requires an OpenAI-compatible embeddings endpoint.
Does session content get uploaded to the cloud?
The archive is local by default and the server binds to 127.0.0.1. The README describes limited anonymous telemetry, which can be disabled with AGENTSVIEW_TELEMETRY_ENABLED=0 or TELEMETRY_ENABLED=0; shared backends, semantic-search endpoints, and Gist export are optional external paths.
Why is an agent or session missing from the UI?
Check that the agent's session directory exists and is configured. Aider scanning is opt-in through AIDER_DIR or agents.aider.dirs; Docker also needs the source directory mounted.
Will cost figures exactly match billing?
Costs are calculated from tokens and available pricing, including cache-token pricing, with LiteLLM and OpenRouter rates plus an offline fallback. When Copilot CLI logs provide billing totals, AgentsView uses those authoritative totals; unpriced models may have no cost value.
Can I open the local server through a remote browser?
Configure --public-url or trusted origins for forwarding or proxy access. If exposing the UI beyond loopback, enable --require-auth; these settings do not create an external listener or proxy.
Is AgentsView Session Archive open source?
Yes. The source code is on GitHub (kenn-io/agentsview) under the MIT licence.
Is AgentsView Session Archive safe to use?
FollowAgents' FARS review (Nov 08, 2026) scored AgentsView Session Archive 19/29 on trust and safety. None of the eight safety controls the review checks for was missing outright. The repository has changed since that review.
Is AgentsView Session Archive still maintained?
Yes. The latest commit on GitHub is from 2026-11-21, within the last 30 days. The latest release is v0.47.0 (2026-11-09).
Who makes AgentsView Session Archive?
AgentsView Session Archive is published on GitHub by the account kenn-io. FollowAgents has not verified which person or company is behind that account.
What is AgentsView Session Archive's official website?
The project's GitHub repository lists https://agentsview.io as its website. That link is set by the repository owner; the source code itself is on GitHub (kenn-io/agentsview).
Was this page helpful?
View on GitHub ↗ Install ↓

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Related concepts