Reads your disk
The transcripts your agents already write. Read-only, always — coSlash never modifies them.
Your coding agents. One live view.
Run more agents / Lose less context
- Read-only
- No account
- Local by default
- Open source · MIT
Know what needs you
Active, waiting, idle, or inactive — across every repo and branch.
Keep the thread
Goals, decisions, files, commits, and every command the agent ran.
Keep going
Resume with context intact, or hand a brief to a fresh agent.
CC
Claude CodeLive now
CX
Codex / ChatGPTLive now
OC
OpenCodeLive now
+
More agentsComing soon
01 — Sessions
Keep moving without losing context.
One place to see what every coding agent is doing.
Waiting on youquestions, permissions, failures
Actively workingwith subagent lineage
Worth a lookwindow filling, cache going cold
coSlashSessions
2 waiting 3 active 9 sessions this week · 5 Claude Code / 3 Codex / 1 OpenCode · $57.80 est. at list API prices
AllClaude CodeCodexOpenCode
WeekMonthAll
ListBoard
Claude Code
Fix double-charge on retried checkout
a3f19c2b
Waiting 40m
Interactive
Asked whether the idempotency key belongs on the payment intent or the order.
$7.43 est.8.23M tok
Codex
Migrate settings page to the new token system
7c04ee81
Active
Autonomous
Rewriting tokens.css and threading ThemeProvider through the settings tree.
$9.32 est.9.92M tok
SUB
audit-color-contrast
gpt-5.6-sol
returned
$0.58372k tok
SUB
find-hardcoded-hex
gpt-5.6-sol
running
$0.24144k tok
Claude Code
Refactor webhook retry into a queue worker
5b8d0417
Idle
Interactive
Worker drains in staging. The dead-letter path and its tests are still open.
ctx 91% · compacted 2× · 14 behind main · cache cold
$23.23 est.25.92M tok
02 — How it works
01
02
03
Your work stays on your machine.
Builds the record
Goals, decisions, files, commands, and subagent lineage, indexed locally. No account, no daemon, no telemetry.
Puts you back in
Resume in your own CLI with full context, or carry a handoff brief into a fresh session — even one from a different vendor.
03 — Resume or hand off
Know whether to resume, before you resume.
Picking a session back up is not always the cheap option. coSlash lays out what it will actually cost to continue, then gives you two ways back in.
Context usedHow full the window is, coloured as it climbs. Past the ceiling the session compacts again, and every compaction trades detail for room.
Prompt cacheWarm or cold, with the 5-minute and 1-hour windows marked. Resuming into a cold cache re-reads the session at full input price — about ten times what a cache hit costs.
DebriefThe goal, the outcome, and up to five key decisions, reconstructed from the transcript. A badge tells you where the goal came from — declared by you, inferred from the session, or the raw first prompt as a floor.
TimelineFirst prompt, questions the agent asked, your answers, recaps, and compactions — each stamped with its turn. Click a category to show or hide it.
ArtifactsFiles changed with per-file counts, commits, PRs, open todos, and every shell command the session ran.
coSlash — Session
127.0.0.1:8787
coSlashClaude Code
Refactor webhook retry into a queue worker
5b8d0417…e2a9
claude-opus-525.92M tok
26h 40m · 9 turns · 174 tools · 4 errors
in 1k · out 142k · cache 24.6M r / 1.18M w
RESUME OR HAND OFFresume-readiness
Context used91% of 1M
Compactions2
Branch+2 / −14 main
Working treeedited 3h ago
Prompt cachecold
DEBRIEFgoal, outcome, decisions
OBJECTIVEMove webhook retries off the request path into a durable queue worker.
OUTCOMEWorker drains in staging. The dead-letter path and its tests are still open.
KEY DECISIONRetry state lives on the job row, not Redis — replays must survive a cache flush.
ARTIFACTSwhat this session produced
9files
0PRs
0subagents
91% context, compacted 2×, 14 behind mainthis one says start fresh
04 — Pricing
Free locally. Pay for collaboration.
The personal attention layer stays free and open source.
Individual
Available now
$0forever
For individual developers
- Local attention board
- Claude Code, Codex, OpenCode, and subagents
- Title, repository, and branch search
- Readiness signals, resume, and handoff
Team
In development
Coming soon
For shared agent work
- Shareable live visibility
- Shareable session discovery
- Cross-person handoffs with context
- Workspace access controls
- SOC 2 Type II
Enterprise
Custom
For organizations with advanced needs
- Everything in Team
- Enterprise deployment options
- Security and compliance support
- Priority onboarding and support
05 — FAQ
The important questions, answered.
What does coSlash read?
The session transcripts Claude Code, Codex, and OpenCode already write to disk, plus the Git and process metadata needed to tell a running session from a finished one. There is nothing to connect and no account to create — it reads what is already on your machine.
Which agents does it support, and on what?
Claude Code, Codex, and OpenCode — both the desktop apps and the CLIs, with subagents shown under the session that spawned them. macOS on Apple Silicon or Intel. Linux and Windows are not supported yet.
Does coSlash change my code or my transcripts?
No. Transcripts are opened read-only and never written to, and coSlash makes no commits, branches, or edits in your repository. It writes only to its own directory, ~/.coslash, where cached debriefs and pending handoffs live. Resume and handoff launch your own CLI in your own terminal — every edit after that is the agent’s, exactly as if you had started it yourself.
Does anything leave my machine?
Not unless you turn it on. Debriefs are derived from the transcript with no model involved. Optional AI synthesis only sharpens them, and stays off until you enable and save it. When on, it sends a bounded set of derived facts — about 12 KB — through the local Claude Code or Codex CLI you pick. That spends a little of the agent’s own usage: a few cents per session at most, and only substantial sessions qualify.
It runs a local server — is that exposed?
No. coSlash binds to 127.0.0.1:8787 and nothing else, and every API request carries an access token minted when the server starts. It is not reachable from your network, and a link from an earlier run stops working once the server restarts.
How are costs calculated?
They are estimates at list API prices, not invoices: token counts from the transcript against a dated per-model price table. A model with no verified price is flagged and left out of the total rather than guessed at, so the number is never quietly wrong. OpenCode sessions report the cost they recorded themselves instead of an estimate.
Can I pick a session up in a different agent?
Yes. Resume reopens the original session in its own CLI with full context. Start fresh writes a Markdown handoff — objective, current state, key decisions, timeline, files, commits, next steps — and opens a new session with it loaded as reference, so the next agent waits for your instruction instead of acting on stale notes. The handoff is plain text, so it crosses vendors: a Claude Code session can be picked up in Codex.
The session ends. The knowledge stays.
Install once, and every session your agents run stays legible — today and three weeks from now.