Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-08-09 · source-backed
Posted to HN August 8, agent-hop searches all your local coding-agent histories and resumes any session in any supported agent, normalizing five on-disk formats to a common turn structure: Claude Code JSONL under ~/.claude/projects/, Codex rollout JSONL under ~/.codex/sessions/YYYY/MM/DD/, OpenCode via SQLite export/import, Pi JSONL under ~/.pi/agent/sessions/, and Grok Build's chat_history.jsonl plus summary.json. Converted sessions are written to look native to the target. Muse Code support was removed pending live API verification, which reads differently in light of today's RuntimeWire story. The format-quirk notes are worth reading on their own if you parse these files for observability: Claude Code hyphenates every non-alphanumeric character in path encoding, Pi is more selective.
Each link below shares sources, entities, or timing with this story.
I check Product Hunt maybe once a week and usually regret it. Today's board is worth reading as market structure. The July 30 leaderboard: SKI at 277 upvotes (free voice input for Claude Code and Codex). AI Search Console at 249 (prompt analytics and citation mapping). Memmy A...
A 29-star MIT terminal UI organizes coding-agent sessions into a hierarchical tree grouped by project, each session in its own tmux pane so agents keep working after the manager closes. Tracks working, waiting, finished, errored, idle, and dead states, supports spacebar quick-...
akitaonrails/ai-memory (1,229 stars, +184 this week, MIT, Rust, 900 commits) inverts the usual design: hooks emit sanitized lifecycle observations during a session, and the server compiles them into coherent wiki pages at session end or PreCompact, "compiled from observations...
Spotify's Portal team published Xirp on August 10: a vendor-neutral agentic development environment that manages concurrent sessions across Claude Code, Gemini CLI, and Codex, each session isolated in its own git worktree so dozens of agents can work the same codebase without...
mikehasa/agentacct (547 stars, MIT, Python, pushed August 7) breaks each agent task into work steps: tools used, files changed, tests run, time and tokens spent, across Claude Code, Codex, OpenCode and others in a local-first dashboard. The no-telemetry positioning is the diff...
claude-mem (89.3K stars) targets seven harnesses. lean-ctx (3.5K stars, Rust, 76 MCP tools) uses 60-90% token reduction as its headline metric. Wienerdog surfaced on HN August 2 offering memory plus self-improving skills for both Claude Code and Codex. All three are harness-ne...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.