mrkeyoor.com_
Sat 15 Aug 16:48 UTC
Dev Toolsevaluationupdated 15 Aug 2026

agentsview

AgentsView turns the local conversation files left by Claude Code, Codex, Cursor, OpenCode, and dozens of other coding agents into one searchable archive. It gives developers a web dashboard and CLI for finding old work, comparing token costs, reviewing tool use, and seeing which projects consumed their agent time.

Verdict

AgentsView is the best fit for developers whose coding history is fragmented across several agents and has become too valuable to lose in raw JSONL files. Its local-first defaults, broad parser coverage, fast search, and unusually detailed usage analysis justify running a small daemon. Install it for exploration and personal recall now, but test a copy of a large archive before relying on it as a complete record, because one hostile source format can still interrupt indexing.

Setup4/5One binary for local use, with archive cleanup sometimes required
Docs5/5Extensive install, source, privacy, backend, and security guidance
Community4/5Fast current development and detailed user bug reports
Maturity3/5Wide coverage, but parser failures can disrupt whole-archive sync

Who it’s for

Developers who regularly switch among Claude Code, Codex, Cursor, OpenCode, and other coding agents.
Teams that need searchable evidence of prompts, tool calls, edits, and model usage across projects.
Cost-conscious users who want local token and price summaries without reparsing raw logs for every query.
Self-hosters who want SQLite locally, with optional PostgreSQL, DuckDB, S3, and Docker paths for larger archives.

Who it’s NOT for

Users with orchestration-heavy Copilot sessions who need complete indexing today: issue #1412 reports that a single transcript line over 100 MB can stop the session archive from progressing.
Trae users with encrypted session stores: issue #1416 reports an endless full-sync loop and sustained CPU use because the source cannot be parsed or excluded.
Administrators who must disable individual agent sources: issue #1417 says empty or nonexistent directory settings still fall back to default discovery.
Anyone treating cost figures as invoices: the README calls per-session cost an estimate, exposes unpriced models, and release 0.40.1 had to correct Kimi usage and pricing.
Security teams unwilling to keep raw agent conversations in a searchable local database: full-text indexing increases the value and sensitivity of the archive, even though the default server stays on loopback.
Users requiring absolutely no outbound telemetry by default: a limited PostHog daemon event is enabled unless an environment setting disables it.

Setup reality

For a normal local archive, the setup is as easy as advertised: install a binary, run agentsview serve, and open the loopback web UI while the first sync builds SQLite indexes. The hidden cost depends on history size and source quality. Large archives can take meaningful time and disk space, every agent stores a different format, Aider and JetBrains need extra configuration or export steps, and encrypted or malformed sources can disrupt reconciliation. Docker requires explicit read-only mounts for every agent directory. Team mode adds PostgreSQL credentials, push jobs, authentication, and a decision about which sensitive transcripts may leave each developer's machine.

One archive for a scattered working life

Coding agents remember a great deal, but they rarely make that memory easy to use. Claude Code, Codex, Cursor, OpenCode, Copilot, and their competitors each write sessions in different folders and formats. Finding why a file changed last month often means guessing which tool did the work, locating its private data directory, and reading JSONL by hand. AgentsView discovers those records, normalizes them into SQLite, and presents one web interface and command line.

The result is more useful than a chat viewer. Full-text search covers message content. The dashboard shows activity, tool and model mix, projects, recent edits, context use, and estimated spending. A session page connects conversation, tool calls, and usage data. Live updates arrive through server-sent events, while HTML export provides a portable record. Optional semantic search can use any OpenAI-compatible embeddings endpoint and cites the conversation unit behind each match.

Breadth is the headline. The README names more than 40 supported sources, including Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Copilot variants, Aider, Goose, Kimi, Qwen Code, and Windsurf. A narrower viewer may be cleaner for one tool, but it cannot answer cross-agent questions about cost or past work.

Local-first is a sensible default

The normal path is one binary and no account. agentsview serve discovers supported folders, syncs sessions into a local SQLite database, and binds the UI to 127.0.0.1:8080. The detached daemon lets the desktop app and CLI share a warm archive, then exits after an idle period when no client or job needs it. Read-only commands can query SQLite directly if the daemon is cold. This is considerate desktop behavior.

Privacy still needs active thought. Agent transcripts can contain source code, terminal output, file paths, pasted credentials, and internal decisions. Full-text indexing puts that material into another high-value file. Keep database permissions tight, protect backups, and scan the archive before publishing an HTML file or GitHub Gist. Semantic search remains local only if its embedding endpoint is local. PostgreSQL push, S3 source roots, and remote DuckDB access deliberately create new data boundaries.

AgentsView sends an anonymous daemon_active event to PostHog at startup and every 24 hours. The documented payload includes app version, commit, operating system, CPU architecture, and a random installation ID, not prompts, projects, paths, accounts, or machine identity. Two environment variables disable it. That is restrained telemetry, but privacy-sensitive deployments should set the opt-out explicitly.

The first sync is where reality appears

Installation options are excellent. The project offers shell installers, Homebrew, Windows packages, macOS builds, Linux archives, AppImages, and a container. Release assets include x86-64 and Arm builds for the major platforms. Version 0.40.1 shipped on August 4, 2026. Most people can be looking at a dashboard within minutes.

Discovery is less uniform because the source applications are not uniform. Aider has no central store, so users must choose roots for a bounded repository scan. JetBrains Copilot requires a separate exporter and repeated exports for fresh data. Current Amp releases may leave only server-side threads, so AgentsView marks that parser deprecated and handles historical local JSON. Antigravity can fall back to a summary unless another local tool produces full transcript sidecars. Docker sees only directories explicitly mounted and configured.

Large or odd archives deserve a copy-first trial. Issue #1412 describes a Copilot orchestration session whose inlined subagent output created a JSONL line larger than 100 MB. The parser rejected it and the wider sync stopped progressing. Issue #1416 reports that encrypted Trae stores can cause repeated full reconciliations and about 300 percent CPU on the reporter's machine. The companion issue #1417 says there is no reliable configuration switch to exclude one discovered agent source. These reports concern version 0.40.1 and were still open on August 14.

Usage numbers are helpful estimates

The usage commands are a strong reason to install AgentsView even if the dashboard is secondary. Daily summaries can filter by agent and date, split by model, account for prompt-cache reads and writes, and emit JSON for a status line or script. Because sessions are already indexed, normal queries do not reread every raw transcript. Per-session output includes total output tokens, peak context, models, missing pricing, and a cost estimate represented as integer microdollars in machine-readable responses.

Do not confuse precision of representation with billing authority. Model names change, agent logs omit fields, providers revise prices, and some models remain unpriced. The latest release specifically fixed Kimi Work tool-step tracking and K2.6 pricing. AgentsView can be excellent for trends, comparisons, and catching unexpected usage. Reconcile material spending against the provider's bill.

Team backends add real administration

A team deployment needs transcript policy, database credentials, authentication, TLS, retention, and project exclusions. PostgreSQL supports shared dashboards, while DuckDB and Quack serve analytics mirrors. The Docker examples bind only to loopback, and the server validates host headers against DNS rebinding. Remote users must configure the public origin, while any non-loopback exposure should require authentication. Those conservative defaults are a genuine strength.

Fast-moving and worth trying

AgentsView was created in February 2026, so its scope has expanded very quickly. The repository was pushed on August 15, the latest stable release arrived eleven days earlier, and detailed parser issues were filed on August 14. Its 93 open count includes issues and pull requests. This is active maintenance, but the 0.x version and current sync failures make archival completeness something to verify, not assume.

For a developer using several agents, the payoff is immediate: old conversations become searchable, costs become comparable, and edits regain context. Start locally, disable sources you do not need when that feature is available, and keep the raw logs as the source of truth. AgentsView is already a very good lens over coding-agent history. It is not yet the only copy of that history you should trust.

Alternatives

ProjectWhat it isPick it when
ccusageA focused command-line tool for reporting coding-agent token consumption and estimated costs.pick this instead when you only need fast usage totals and do not want a searchable transcript archive or web dashboard.
Agent Session ViewA web and terminal viewer for browsing and exporting Claude Code and Codex sessions.pick this instead when Claude Code and Codex cover your workflow and a smaller viewer is preferable to multi-agent analytics.
Claude Code LogA Python CLI that converts Claude Code JSONL transcripts into readable HTML or Markdown.pick this instead when you need portable Claude Code exports, not a continuously indexed service.

What people are saying

  1. [github-trending] kenn-io/agentsview

Sources

  1. AgentsView README
  2. AgentsView v0.40.1 release
  3. AgentsView issue #1412: long subagent sessions
  4. AgentsView issue #1416: Trae reconcile loop
  5. AgentsView issue #1417: source exclusion
  6. AgentsView issue #1418: cwd filtering