Changelog · 42 recent releases
What shipped.
The latest releases across the toolkit, newest first. Each entry links to its release notes on GitHub.
Releases
Newest first.
touchless-mac · v0.1.1
touchless-mac 0.1.1 makes setup feel like a finished product: one command installs it, the hand models come in the box, and touchless-mac doctor tells you exactly what's left to switch on.
touchless-mac · v0.1.0
The first release of touchless-mac: control your Mac with your hand through the built-in camera. Everything runs on your Mac; nothing is sent anywhere.
SuperLocalMemory · SuperLocalMemory v4.2.13
Three fixes for large stores, from reports on #306 and #304. No migration and no command to run.
SuperLocalMemory · SuperLocalMemory v4.2.12
Fixes for six reports filed after 4.2.11. No migration and no command to run.
SuperLocalMemory · SuperLocalMemory v4.2.11
Three fixes for things that looked done but were not. Upgrading runs one migration (M067, one trigger) and needs no command; a graph copy that already drifted is rebuilt by the daemon on its own within about ten minutes.
ModStage · ModStage 0.0.20
Hermes (Nous Research) is a built-in agent, started over ACP (hermes acp). Install: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash. The launcher says so before Start when Hermes's own approvals.mode is off.
ModStage · ModStage 0.0.19
The band above the prompt respects the row budget. Asked for in the listing review: the engine tells the band area how many rows it has (maxRows). With none, ModStage's band steps aside and every other mod's band stays; with one or two rows it draws one compact row (title,…
ModStage · ModStage 0.0.18
The pane could not be scrolled while a run was streaming (P1). Two causes. 0.0.17 drew the head's pictures in frames (isInteractive) so they would animate, and a frame swallows the mouse wheel; every picture is an ordinary image again (the animation is CSS, as in 0.0.16), and…
ModStage · ModStage 0.0.17
The panel's own logo, and robots in its style. The header carries ModStage's real logo (the four robots from the README) instead of a mark invented for 0.0.16, and each agent's robot is redrawn in the logo's family: a flat, rounded head in the agent's colour with a navy…
ModStage · ModStage 0.0.16
The desktop head never ran text into a neighbour. At the narrowest panes the header, the stat tiles and the run card now stack or shorten instead of overlapping; the bridge's problem line is shown on the desktop too; a custom agent's colour that is not a plain hex value is…
ModStage · ModStage 0.0.15
ModStage hid every other mod's band above the prompt. Its band never asked the mods beneath it for theirs, so while ModStage was installed, context-bar, token-weather, cache-tax's keep-warm row and any other mod that draws above the prompt showed nothing. ModStage is an…
SuperLocalMemory · SuperLocalMemory v4.2.10
If you edited a memory (the dashboard's Edit button, the updatememory tool or slm update) and applied the correction, a question could no longer find it. The old text was retired and the new text was saved, but the new text was never added to the search index, so only exact…
SuperLocalMemory · SuperLocalMemory v4.2.9
If you run Mode B with Ollama, every saved memory used to cost up to eleven model calls, most of them wasted. A machine with a steady stream of memories kept Ollama busy all day, and recalls waited behind it. Nothing to run after upgrading.
SuperLocalMemory · SuperLocalMemory v4.2.8
Upgrading runs a few one-time repairs automatically the first time the daemon starts. Nothing to run. Every repair keeps an undo record, and slm doctor shows what each one did.
SLM MCP Hub · v0.3.4 — resultType for MCP 2026-07-28
Fixes the hub showing tools fetch failed — missing required resultType in Claude Code 2.1.292 and any other client that speaks MCP protocol revision 2026-07-28.
Jev Decision Layer · 1.0.15
Decisions sent through OpenRouter are no longer refused. OpenRouter names the dated version of the model that answered, and Jev treated that as a different model. A dated version of the requested model is now accepted, nothing else is, and the local receipt records which…
Jev Decision Layer · 1.0.14
On Linux, the setup and workbench commands exit as soon as they finish.
Jev Decision Layer · 1.0.13: Jev, Laya, or both
Local Laya setup, seventeen new recipes, and hardening throughout.
Jev Decision Layer · Qualixar Jev Decision Layer 1.0.12 — Name the Policy That Blocks It
When an organization manages Claude Code, its policy can stop the Jev plugin's hooks, keep the plugin from loading, or leave its MCP server off an allowlist. Until now the plugin just went quiet and nothing said why. A tool that stops working without a word is a reliability…
Jev Decision Layer · Qualixar Jev Decision Layer 1.0.11 — Approve Once, Every Harness
Qualixar Jev Decision Layer lets a coding agent hand small, consequential choices (which tool, which task, which files matter, whether an extraction matches its source) to TypeSafe Jev, then continue through the host's own permissions. It is part of Qualixar's AI Reliability…
Jev Decision Layer · Qualixar Jev Decision Layer 1.0.8 — Fast, Typed AI Agent Decisions
When an agent reaches a small but consequential choice—tool, task, test, or review path—it can ask TypeSafe Jev, a model built for fast typed decisions, and continue through the host's normal controls. Qualixar Jev Decision Layer makes that flow reusable across harnesses.…
Bounded Loops · bounded-loops 0.7.6
Native Antigravity lifecycle-hook repair.
Bounded Loops · bounded-loops 0.7.5
Hermes public-install compatibility repair. Users of 0.7.4 should upgrade before native Hermes installation.
Bounded Loops · bounded-loops 0.7.4
Native Hermes plugin support, an additive bridge v2 producer, and release-pinned runtime support.
Bounded Loops · bounded-loops 0.7.3
Fixes bl capabilities so loop and graph terminal states render separately.
Bounded Loops · 0.7.2 — a forged evidence digest could reach the receipt
Two fixes from an audit for one specific defect shape: a check whose criterion is applied to a value the party under scrutiny controls. Both were confirmed by writing the exploit first.
Bounded Loops · 0.7.1 — the MCP handshake reports its version
One fix. The MCP server did not report its own version.
AgentAssert · 0.7.0 — universal Type C enforcement
Enforcement is no longer tied to a vendor. Until now a contract could only be enforced through an LLM wire format, a vendor SDK client, or the Claude Code hook — and the framework integrations could only measure. This release makes enforcement available anywhere an agent runs.
AgentAssert · 0.6.0 — paper–code parity, enforcement state fix, drift calibration
Closes the gaps between the published paper and the shipped package, and fixes two defects that produced confidently wrong numbers.
AgentAssert · agentassert-abc 0.5.0 — runtime enforcement plane
0.5.0 adds a runtime enforcement plane — real-time ALLOW/DENY/REDACT/MODIFY decisions on tool calls and model responses — alongside the existing measurement and certification planes. New zero-code-change adoption surfaces ship as optional extras: agentassert-abc[sdk] (wrap()…
AgentAssert · v0.4.0 — Dependence-aware compositional reliability certificate
Dependence-aware compositional reliability certificate that does not assume stage-failure independence (C5):
SLM MCP Hub · v0.3.3 — legacy era-probe fallback
Strict legacy stdio backends no longer fail to connect.
SLM MCP Hub · v0.3.2 — dependency surface correction
The hub no longer installs a memory engine in order to talk to one.
SLM MCP Hub · v0.3.1
CLI management commands now authenticate against auth-enabled hubs (#29). When SLMHUBAPIKEY is set, slm-hub tools, status --verbose, reconnect, the server subcommands (list, reload, add, remove, modify, status), and the observability commands (servers, health, warm, stop) now…
SLM MCP Hub · SLM MCP Hub v0.3.0
Universal, local-first MCP gateway. pip install slm-mcp-hub or npm install -g slm-mcp-hub.
SkillFortify · v0.6.0 — unified skill discovery, reproducible experiment harness
Discovery is now uniform across formats. All skill formats share one bounded tree walk, so OpenClaw install roots and MCP configurations are found anywhere below the scan root — matching the behaviour already provided for Claude skills. A single scan of a repository now…
SLM MCP Hub · v0.2.6 — credibility reset
Credibility-reset release for SLM MCP Hub.
SkillFortify · v0.5.0 — full-surface discovery, graded findings, rebuilt benchmark
Discovery now covers every path the runtimes actually load skills from — personal, project, plugin and nested-package .claude/skills/, legacy .claude/commands/, and .openclaw/skills/ — following symlinks and de-duplicating on resolved path. MCP configuration discovery covers…
AgentAssert · v0.3.0 — AgentAssert
Formal Behavioral Contracts for AI Agents
SLM Mesh · v1.1.0 — Skills, Integrations & Demo
/mesh-peers — Discover active sessions /mesh-send <message — Send or broadcast messages /mesh-lock <file — Lock/unlock/query files /mesh-status — Full mesh dashboard /mesh-sync — All-in-one coordination
AgentAssay · v0.1.2 — Production Release
Fully production-grade release with zero CI warnings.
AgentAssay · v0.1.1 — Initial Public Release
Test More. Spend Less. Ship Confident.