Search

AI model: XcaliburMoon/gemma-4-E2B-it-agent-posttrain

Portable cross-agent review, PR workflows, and shared skills

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.

LSP action surface for DeepSeek Harness: diagnostics, formatting, completion, code actions, symbols, signature help, inlay hints, and rename tools over language servers

Official-grade GitHub CI for DeepSeek Harness: composite action.yml, PR review bot with idempotent inline comments and a status-check gate, plus PR/issues tools with every write gated by human approval (Apache-2.0, dsh-plugin).

Cross-device DeepSeek Harness session sync: a dedicated git mirror with append-only keep-both conflict resolution (fork files, never silently overwritten), /sync command and sync_* tools

Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-to-interrupt.

OpenTelemetry and Langfuse observability exporter for DeepSeek Harness: turn/step/tool/LLM spans, token and cost metrics, sanitized prompt/completion capture, async batching, bounded offline buffering, retry with backoff

Vendor parameter translation and deterministic JSON repair for DeepSeek Harness: /translate maps temperature/top_p/max_tokens/stop/system across 11 vendors, and the post-execute repair layer (plus fix_json) fixes broken JSON tool output without ever fabricating data

PII masking middleware for DeepSeek Harness: anonymize names, phones, emails, ID cards, bank cards, keys, and addresses to placeholders before they reach the model, restore them at the display layer, keep the restore table only in memory and a controlled storage domain, never log plaintext, and expose /mask and the mask_test tool

Unified static-image generation router for DeepSeek Harness: one image_generate tool with standard parameters, config-driven engine routing (OpenAI Images, Zhipu CogView, and any compatible endpoint) with health-aware fallback, durable workspace attachments, per-session quota accounting, and a Plugins settings panel

Read-only performance diagnostics for DeepSeek Harness: session load/restore timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via /fast, persisted as reconstructable session events with async sampling off the model path.

Laya decision engine as a first-class Cordis service and model-visible tools for DeepSeek Harness.

No description available

Aphasia Agentry - canary-proven breach and attack simulation for AI agents (OWASP LLM Top 10)

Client for kept.vision keepers — versioned, signed, append-only storage for agents. Early release: the client is not published yet.

The integrity layer for your evals: fail-closed release gates with signed, tamper-evident, pre-registered receipts — for pytest, promptfoo, claude plugin eval, or any scores. Runs in any CI, no AI agent required.

Agent-plane presentation selector: composes one agent's tools as Code Mode, native, or both

Validate, repair, retry, and safely consume structured LLM output.