Open source Grok Bot alternative, Bring your own agent and subscription: message Claude Code, Codex, Gemini CLI, Cursor, Copilot and 40+ AI agents as bots on your own computer, from iPhone, Mac, Windows, Linux or terminal. Agent-agnostic and free. Also a Muse and Dots alternative. Built in Rust.
Roadmap
Status: proposed, 2026-11-03. Four long-running tracks, in the order the owner listed them. Each track links to the doc that holds its current behavior and its detailed plan. Shipped work stays in those docs, not here; when a track finishes a step, update its plan doc in the same change and trim the item below.
Rules that apply to every track: CLAUDE.md (version bumps, e2e, cross-platform UI), docs/plans/ (detailed plans), docs/archive/ (finished plans).
1. Cloud plan
Goal: users who want their bots on a cloud computer bring their own sandbox, with no charge from Codync and without changing how the host owns the logic.
Where it stands:
- The Codync cloud already carries the encrypted relay (
cloud/, ComputerRelay DO), accounts, public routine webhooks and the cloud assistant connector (mcp.codync.dev, cloud assistants). - A private relay is supported and has no accounts (relay reference).
- The product direction (owner, 2026-11-06): Codync charges nothing, and users bring their own sandbox and API key. Memoh (self-hosted per-bot cloud computers) is a possible option; its role is not decided yet.
feat/cloud-boathas the cloud computer flow on Boat, so far with one Codync-held key.cloud/is deployed by hand, never by CI (deployment).
Next steps:
- Decide how users bring a sandbox: which providers come first and where their API key lives. Write the decision in
docs/design/before building. - Prove one end-to-end path: sign in, start a cloud computer on the user's own sandbox, pair a phone, run a bot, read the reply.
Done when: a new user can bring a sandbox, get a working cloud computer, and use it from the iPhone and desktop apps with no local computer, and the relay docs describe it.
2. codync-network: long-term upkeep and stable bot-to-bot exchange
Goal: computers on several networks keep talking as the set of agent types grows, and bot-to-bot messages behave the same whatever agent is on each end.
Where it stands: codync-network, what's left, and bot collaboration. Still open there: Codync-run relays (waiting for the owner to rent servers), the account networks, and the screen and rules items in the plan.
Next steps:
- Close the open packages in
plans/codync-network-next.mdin build order; move finished ones into the feature doc. - Conformance tests for bot-to-bot exchange: one fixture per agent type (Claude, Codex, and each ACP registry agent that can run a bot), checking the same message flow: request, reply, timeout, refusal, and a routine that a bot may not run for another bot.
- Keep
host/crates/networkat its 0.x version rule: every release that changes it bumpscodync-network. - Upkeep: each release, run the conformance set against the current agent versions and record failures in ACP adapter workarounds when they come from an adapter.
Done when: the conformance set passes on every supported agent type across two computers, on the same network, in CI or in a documented manual run, and the network docs list no open "Beta" gaps.
3. Memory (codync-mem): benchmarking and optimization
Goal: measure how well bot memory works, then improve it with numbers, not guesses.
Where it stands: context and memory and the design in
bot memory. Bot memory is files (MEMORY.md and notes) that the bot edits; dreaming tidies them
into topic notes. The open choice is between a harness's own memory and codync-mem
(harness memory).
Next steps:
- Write a benchmark set: a fixed script of conversations per bot, with questions whose answers depend on earlier
sessions. Keep it in
host/crates/memorytests or a fixtures folder; no real user data. - Metrics: recall (right fact returned), precision (no wrong or stale fact), tokens added to each turn, time to first token, and notes size after N dreams.
- Run it on the current memory, then on the harness-memory option, and publish the table in
docs/reference/. - Optimize the worst metric first. Keep the rule that memory is never full: dreaming moves detail into topic notes.
- Use the result to decide the harness-vs-
codync-memquestion, and record the decision in the harness-memory plan.
Done when: the benchmark runs from one command, its results are in the repo, and the default memory choice is backed by those results.
4. ACP coordination and long-term maintenance
Goal: every agent that Codync drives over ACP keeps working as adapters change, and the patches around them shrink over time.
Where it stands: the host drives agents over ACP (host/src/agent/acp.rs, host/src/agent/bot/). Each adapter bug
patched in the host has a row in ACP adapter workarounds (last checked
2026-11-02). Open upstream items include codex-acp#647 (429s and other errors sent as reply text) and the JetBrains AIR opt-in that works around it.
Next steps:
- Make the adapter check a routine: on each release, check every registry adapter version against the workaround table; delete rows whose upstream fix has shipped, and add rows for new bugs in the same change.
- Track upstream issues in one list (owner, status, which workaround it unblocks) and re-check it on the same cadence.
- Once an adapter's rows are mostly gone, reconsider its place in the registry, or whether another implementation is worth it. Record the decision in the workarounds doc.
- Keep the ACP parser tolerant (updates stay
serde_json::Value), and add a test for each new adapter variant seen in the field.
Done when: the workaround table is checked on every release, each row names an upstream issue or a delete condition, and no adapter is patched in code without a row.
Order and dependencies
- Track 1 (cloud) sets the cloud option; it does not block the others.
- Track 2 needs the adapter list from track 4, so run track 4's routine check first.
- Track 3 feeds track 1 if cloud computers need a memory default.
Open questions
- Which sandbox providers can users bring first (Boat, Memoh or others)?
- Does the memory benchmark run in CI, or as a manual run on a dev computer?
- Who owns the adapter check each release (a routine, or the release checklist)?