ResearchSession Capture Research
11 — Open-Source Exporters and Viewers
11 — Open-Source Exporters and Viewers
Research conducted: 2026-07-03; stars and activity dates from the GitHub API on that date (tier B/C — repos and readmes; none source-audited except where noted). Record schema per the brief. Baseline for comparison: SpecStory CLI, 1,268★, Apache-2.0.
Pattern across the whole category: every serious OSS tool reads the agents' native stores (vector A in Déjà Vu terms). None wraps a PTY; one (claude-trace) patches fetch to see wire traffic. The market has independently converged on SpecStory's mechanism.
Multi-agent tools (closest to SpecStory scope)
claude-replay — replay as a portable artifact
- What/maker: session logs → self-contained interactive HTML replays; solo dev es617. MIT, free.
- Surfaces: Claude Code, Cursor, Codex, Gemini, OpenCode.
- Mechanism: reads native local stores (JSONL incl. tool calls, thinking, timestamps); read-on-demand, no daemon.
- Output: one static HTML file per session — step-through player, timeline, tool-call inspection; shareable by copying the file.
- Maintenance: 743★, pushed 2026-06-02; Show HN 2026-03-06, 105 points (HN).
- Differentiator: replay-as-artifact vs SpecStory's continuous markdown pipeline.
- Sources: github.com/es617/claude-replay.
coding_agent_session_search — the retrieval heavyweight
- What/maker: unified Rust TUI/CLI full-text search over local session history "across 11+ providers"; Jeffrey Emanuel (Dicklesworthstone). Free (non-standard license — GitHub reports NOASSERTION).
- Mechanism: indexes each agent's native store read-only; no capture step at all.
- Maintenance: 938★, pushed 2026-07-03 (same-day activity).
- Differentiator: broadest provider coverage in this sweep; solves the retrieval half of SpecStory's proposition without owning capture. SpecStory only reached indexed search in v2.0.0 (2026-06-29).
- Sources: github.com/Dicklesworthstone/coding_agent_session_search.
claude-code-tools / aichat search
- What/maker: agent-productivity toolkit whose
aichat searchbuilds a Rust/Tantivy full-text index over sessions of Claude Code, Codex, "and similar CLI agents"; Prasad Chalasani. MIT. - Maintenance: 1,885★, pushed 2026-06-30.
- Sources: github.com/pchalasani/claude-code-tools.
agentlore — team aggregation (embryonic)
- What/maker: "team visibility layer" aggregating agent logs to a Go server with shareable permalinks; clkao. MIT. 11★, pushed 2026-03-19.
- Differentiator: the only OSS attempt at SpecStory-Cloud-style team sharing found; too early to lean on.
- Sources: github.com/clkao/agentlore.
Long tail (all under 10★, verified alive 2026-07-03)
recall (Apache-2.0, desktop browser), tessera, agents-session-viewer, chathistory (HTML/PDF export).
Claude Code-specific
| Tool | What | Mechanism | Output | Signals (2026-07-03) |
|---|---|---|---|---|
| claude-code-log (daaain) | JSONL → HTML/Markdown, project browsing, TUI | reads ~/.claude/projects/**/*.jsonl | HTML + MD, local | 1,126★, pushed 2026-07-02 — the de-facto standard converter |
| claude-code-transcripts (simonw) | publish sessions as multi-page HTML | reads JSONL; --gist uploads for a shareable URL; orgs deploy SSO-gated transcript sites (writeup) | HTML site / gist | 1,597★, pushed 2026-02-12 |
| claude-code-history-viewer | desktop GUI browser + token/usage analysis | reads ~/.claude | desktop app | 1,747★, pushed 2026-07-01 |
| claude-code-viewer (d-kimuson) | web client: browse past + drive live sessions | reads JSONL, wraps live runs | local web app | 1,239★, pushed 2026-05-10 |
| claude-conversation-extractor | bulk extract + search UI | reads JSONL | MD/text/JSON | 628★, pushed 2026-01-02 |
| claude-history | Rust fuzzy-search TUI over history | indexes JSONL incl. tool output | TUI | 364★, pushed 2026-06-29 |
| cctrace | export to Markdown + LLM-ingestible XML | reads JSONL | MD/XML | 199★, pushed 2026-01-06 |
| claude-trace (Mario Zechner) | records all API traffic incl. system prompts | fetch-patch wrapper around claude (vector D — the only non-file-reader here) | JSONL traffic + HTML views | npm v1.0.9 2026-04-16; low activity |
| cclogviewer | JSONL → HTML review UI | file read | HTML | 84★, pushed 2025-08-08 — dormant |
| claude-code-exporter (developerisnow) | MD export/aggregation + MCP | — | — | npm alive, GitHub repo deleted — abandoned |
Smaller: claude-notes (76★), claude-insight (75★), ccrecall (transcripts → SQLite, 22★, pushed 2026-07-02), claude-session-export, claude-code-log-analyzer (21★).
Cursor-specific
| Tool | What | Signals |
|---|---|---|
| cursor-chat-browser | web browser over all Cursor chat/composer history (reads workspace state.vscdb) | 515★, pushed 2026-03-16 — best-known |
| cursor-view | local web app: browse/search/export/share all projects (Apache-2.0) | 127★, pushed 2025-09-12 — slowing |
| cursor-chat-export | Python CLI → Markdown | 248★, pushed 2024-08-30 — stale ~2 years, predates Composer storage changes; likely broken on modern Cursor [UNVERIFIED] |
| Cursor-Chat-Exporter | — | 53★, 2024-12-30 — stale |
The graveyard rate here is the Cursor-schema-churn story from 01 seen from the OSS side: unfunded maintainers stop chasing state.vscdb changes.
Copilot- and Codex-specific
- Copilot cluster (native export is JSON-only, so small tools fill the gap): fengzehan's Copilot Chat Exporter and Copilot Chat to Markdown (VS Marketplace), github-copilot-chat-exporter (PowerShell, 5★, 2026-04-26), copilot-chat-export-formatter (dead, 2023). All read
workspaceStorage/**/chatSessions/*.jsonor drive the built-in export command. - Codex cluster (no dominant viewer exists): @nogataka/codex-viewer (npm v0.0.11, 2026-02-05, 35★), codex-session-viewer (2★), codex-history-list (10★), plus ~5 more ≤2★ repos. All parse
~/.codex/sessions/**/rollout-*.jsonl. The niche is unconsolidated — nobody owns Codex history tooling.
Category read-out
- Mechanism monoculture: native-store reading won everywhere; wire interception (claude-trace) exists only for depth (system prompts/thinking), and PTY scraping appears nowhere.
- Claude Code has a rich, healthy tool belt; every other agent's ecosystem is thin or stale. Cross-agent tools are new (2026) and retrieval-focused.
- Sharing is the unsolved half: gist upload (simonw) and static HTML files (claude-replay) are the state of the OSS art; only embryonic agentlore attempts team-level aggregation.
- Maintenance risk correlates with store stability: Cursor exporters die fastest; Claude Code JSONL readers live longest — matching Déjà Vu's "pair unstable formats with a vendor-blessed hedge" stance.