Skip to content

Latest commit

 

History

History
37 lines (27 loc) · 3.63 KB

tahira.md

File metadata and controls

37 lines (27 loc) · 3.63 KB

Tahira: Core (engine) and Memory

Repos: codehands-runner (week 1), codehands-contracts (shared with Midhat), codehands-engine and codehands-runtime (from week 2), codehands-memory (from month 1, week 2).

The goal: a task goes in, a reviewed change comes out, nothing the model does can touch the host, and the second run on a repo is better than the first.

Month 1, week by week

Week Repo Build Friday demo
1 · Oct 19 to 23 runner, contracts Run Claude Code and Codex in a worktree per task. Events, stop, resume, approve, reject. Repo notes. Contracts frozen Friday From the phone, a task runs in its own copy of the repo, and approving it puts the change on a branch (guide)
2 · Oct 26 to 30 runtime, engine, memory The repo's commands run in a locked Docker box. The engine moves a task through analyze, plan, implement, test and review, saving each step, with the same events as the runner. MemoryStore contract and stand-in. Repo profile v1 Pick "Code Hands engine" in the app and watch it go step by step
3 · Nov 2 to 6 runtime, engine, memory Tools: list, read, search and patch, limited to the repo. Test step and a repair loop capped at 2. Memory: a tree-sitter symbol index and a repo map Our engine fixes a small bug and the change shows on the phone
4 · Nov 9 to 13 engine, memory Review step. Checkpoint after every step, resume after kill -9. Tests that try to trick it. The second task starts with what the first learned M1: kill the daemon halfway and the task still finishes

Plug-ins: daily in week 1 with Midhat. Oct 30: engine in both apps (Midhat), step recording (Talha). Nov 6: model per step (Memoona).

Months 2 to 6

Month Core Memory Done when
2 YAML workflows, external agents as a step, approval gate, two runs at once in separate worktrees Hybrid search (sqlite-vec plus BM25), user memory, recall in the plan step under a token budget A three-step workflow with one external agent step resumes after a crash. A table of plan quality with memory on and off
3 Branch per run, PRs through a GitHub App, video verify, hardening Context compaction, memory viewer data, memory as editable markdown The team uses it daily for a week with no manual DB edits
4 Router hooks, parallel candidates, a queue with leases shared by two daemons Learning from eval results, shared notes across models, sync protocol with vector clocks A measured gain from memory on 50 tasks
5 Worker image, laptop to cloud handoff with a git bundle Sync service, encryption with per-user keys A remote worker uses memory written on the laptop an hour earlier
6 gVisor option, Firecracker spike, threat model, v0.1 Self-hosted sync, retention and delete-everything controls Self-hosted with privacy controls documented

Weekend reading, month 1

Before week Watch or read Spike
1 Claude Code headless mode, CLI reference, git worktree, codex exec claude -p on the fixture repo, save the JSONL
2 Docker in 100 Seconds (Fireship), the Docker getting started guide, XState concepts, the Drizzle SQLite quickstart npm test in a container: 1 GB, no network, 60 s
3 A 10-minute SWE-agent or OpenHands demo, the git apply man page, the tree-sitter playground Apply a patch from Node that refuses ../secret
4 Stripe on idempotent requests, the Letta quickstart kill -9 a run mid-step, restart, see what it takes to continue

The deeper learning kits for months 2 to 6 are in the plan, under SIG Core and SIG Memory.