OpenClaw
Slack approval QA checkpoints and Telegram poison fix land
OpenClaw ships Slack approval checkpoints for verifiable artifact proof and stops Telegram's isolated-ingress loop on missing harnesses.
read --wire →
$ tail -f topics/ai-agents.log
Daily updates from the AI-agent and agentic-coding ecosystem - LangChain, OpenHands, Cline, and LlamaIndex. What shipped this week in the frameworks and coding agents developers are building on.
69 updates across 2 projects this week.
One calm review of what shipped across AI Agents - the commits, releases, and security advisories that matter. Every Monday, with security advisories same-day. Free, unsubscribe in one click.
We'll start you on the top AI Agents projects - refine anytime. · Read a sample issue →
OpenClaw
OpenClaw ships Slack approval checkpoints for verifiable artifact proof and stops Telegram's isolated-ingress loop on missing harnesses.
read --wire →
OpenClaw
OpenClaw now awaits agent_end hooks in local CLI and Codex terminal paths, and auto-reply sessions survive compaction failures.
read --wire →
OpenClaw
openclaw's doctor now flags plaintext secrets in config and the remote TUI skips plugin-heavy startup work, trimming cold start.
read --wire →
OpenClaw
Package publishes now survive Convex write contention, and doctor checks validate Cloudflare and other providers read-only.
read --wire →
OpenClaw
ClawScan security classification now routes through a queued Codex worker that overrides VirusTotal decisions, making telemetry-only and trusting verified @openclaw/* packages by default.
read --wire →
OpenClaw
OpenClaw hardens skill transfer acceptance against banned requesters and sanitizes Codex image payloads against replay attacks.
read --wire →
OpenClaw
OpenClaw ships a stale-bootstrap fix, Feishu CardKit stream handling, a checkpoint ledger, and a dry-run diff for path edits.
read --wire →
OpenClaw
Provider drift classification is now a shared policy across live tests, plus a config-repair fix closes a gap where the latest broken config copy was silently dropped.
read --wire →
OpenClaw
Gateway agent-event streaming gets throttled with cumulative delta buffering, and iOS regains its privacy permission prompts.
read --wire →
OpenClaw
OpenClaw's iMessage monitor now treats Apple rich-link preview wrappers as metadata rather than user media, so pasted URLs keep flowing through the text path.
read --wire →
OpenClaw
The Windows node connection layer shipped a major refactor plus a batch of bug and security fixes, while OpenClaw core tightened test assertions across Telegram and provider flows.
read --wire →
OpenClaw
The Windows node now speaks v3 signaling exclusively, fixing the most disruptive connection failures and removing the now-dead discovery UI.
read --wire →
OpenClaw
The substrate's path engine shed YAML support and several speculative grammar features, replacing a hand-rolled MD parser with markdown-it.
read --wire →
OpenClaw
Two gateway patches remove ways for callers to bypass ownership checks, and a workspace addressing subsystem ships alongside them.
read --wire →
OpenClaw
ClawHub makes security review badges neutral [ref:7], while OpenClaw improves Discord voice capture [ref:2] and trims reply queue churn [ref:3].
read --wire →
OpenClaw
OpenClaw's Telegram picker now displays the active thinking level, and Gateway's loopback proxy bypass only targets the intended authority.
read --wire →
OpenClaw
OpenClaw fixes channel recovery after stop timeouts so auto-reconnect state isn't poisoned.
read --wire →
OpenClaw
OpenClaw tolerates a missing image optimizer under the size cap and caps Gateway session listings at 100 rows by default.
read --wire →
OpenClaw
WebChat now explains compacted history boundaries and offers one-click recovery, while the gateway models.list path gets a read-only persisted fast path.
read --wire →
OpenClaw
OpenClaw is consolidating session lifecycle management by adding a simpler thread-bound spawning path and removing an obsolete configuration knob in the same effort.
read --wire →