threadle
What your coding agents did while you weren't looking
Details
- External ID
- 1257306
- Source
- PH
- Company
- —
- Product
- threadle
- Website domain
- producthunt.com
- Launched
- Sept. 22, 2026
- Cohort
- —
- Upvotes
- 1
- Upvotes percentile
- 0.30815693820825313
- Tags
- Open Source, Developer Tools, Artificial Intelligence, GitHub
- Fetched at
- Sept. 23, 2026, 1:01 a.m.
- Updated at
- Sept. 23, 2026, 1:01 a.m.
Description
Claude Code, opencode, Cursor, Antigravity, Codex, Copilot and Grok write down everything they do: every file read, every tool call, every token spent. Almost nobody reads it. threadle does, and draws it as one graph. Walk the timeline, diff what changed, trace lineage across runs. Then hand context from one agent to another and wire sessions into pipelines. Localhost, no account, no telemetry, no outbound requests.
Enrichment
- Theme
- Claude integrations and coding agents
- Vertical
- Horizontal
- Function
- Observability & eval
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Commercial product
- Normalized one-liner
- observability and audit logs for ai coding agents
- Manually corrected
- False
Could you build this?
Partial The UI and basic MCP server wrapper are vibe-codeable, but parsing heterogeneous, rapidly shifting telemetry/log formats across half a dozen distinct agent tools while orchestrating robust cross-agent execution is complex.
What it would actually take: The architecture involves a local Go or Rust daemon reading proprietary local SQLite and JSON transcript stores for Claude Code, Cursor, Copilot, and others, paired with a React/Canvas visualizer. The tricky parts are maintaining reverse-engineered log parsers for undocumented CLI tools, orchestrating parallel agent execution graph pipelines, and handling process lifecycle and spend estimation without native API hooks.
Competitors
Other products that read as similar to this one — 262 launches clear the similarity bar, closest 8 shown.
Attention rank: #173 of 263 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 313 days after the earliest competitor.
- Drawa · ph · 2026-09-30 · 2 upvotes · similarity 0.53
- Claudescope · ph · 2026-09-17 · 1 upvotes · similarity 0.50
- Agent Flow: A beautiful way to visualize Claude Code actions · hn · 2026-03-26 · 5 upvotes · similarity 0.48
- Lazyagent · hn · 2026-04-12 · 8 upvotes · similarity 0.47
- Lazyagent · hn · 2026-04-15 · 8 upvotes · similarity 0.46
- Agent Skills by stark AI · ph · 2026-09-15 · 3 upvotes · similarity 0.46
- CCC · ph · 2026-09-10 · 3 upvotes · similarity 0.45
- I am running 3 coding agents non-stop over the last 3 days. Here is how · hn · 2026-06-13 · 10 upvotes · similarity 0.45
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a observability & eval tool for Media & entertainment yet.