Awesome DeepSeek Harness
Section: Memory & Knowledge · OpenViking memory/context plugin for DeepSeek Harness: connects dsh to OpenViking's self-evolving context database for cross-session agent memory and knowledge RAG.
Entry
Appears in 8 awesome lists
ByteDance/Volcengine's open-source context database that puts an agent's knowledge, memory, and skills in one virtual filesystem under viking://, navigated with ls/tree/read/grep and inspectable by humans instead of hidden in an embedding store. Every directory carries generated L0 abstracts and…
Section: Memory & Knowledge · OpenViking memory/context plugin for DeepSeek Harness: connects dsh to OpenViking's self-evolving context database for cross-session agent memory and knowledge RAG.
Section: Context Delivery & Compaction · ByteDance/Volcengine's open-source context database that puts an agent's knowledge, memory, and skills in one virtual filesystem under viking://, navigated with ls/tree/read/grep and inspectable by humans instead of hidden in an embedding store. Every directory carries generated L0 abstracts and…
Section: Scoring & Ranking · Reranking: Volcengine's agent context database ships a Jev rerank client that scores each candidate document with jev-latest against api.typesafe.ai and treats the returned probability as relevance, because TypeSafe exposes no native rerank endpoint.
Section: 4. Agentic AI & Multi-Agent Systems · Open-source context database for AI agents that unifies agent memory, knowledge RAG, and skills as a virtual filesystem. AGPL 3.0 licensed.
Section: Other · Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Section: 数据库与存储 (Database & Vector) · 上下文数据库。火山引擎开源,专为 Agent 长期记忆与分层上下文管理设计。
Section: AI and Agents · A context database for AI agents that unifies memory, resources, and skills.
Section: Memory & Knowledge Systems · Context database that unifies agent memory, knowledge retrieval, and skills behind an MCP-accessible storage layer.
Indexes coding-agent sessions already written to disk and serves them back over MCP with no LLM calls, embeddings, or API keys. The zero-dependency binary solves the memory cold-start problem for cross-session persistence and demonstrates that agent memory can be built on existing filesystem…
Coverage, security and code quality for coding agents. Gemini CLI extension that runs the project's existing tests, measures line, branch and MC/DC coverage, and hands Gemini the untested code to test next. Install with gemini extensions install https://github.com/supercorp-ai/supercov.
Anthropic — https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents · blog — Anthropic's primary statement that the harness's job is engineering context (editing, compaction, memory, programmatic tool-calling) — the mechanism behind why same model + different harness…
MCP server and CLI that injects up-to-date, version-specific library documentation directly into agent context, eliminating hallucinated APIs and outdated code examples caused by stale training data. Ships as both a ctx7 command-line tool and an MCP server with resolve-library-id and query-docs…
High-performance code intelligence MCP server that full-indexes repositories into a persistent knowledge graph via tree-sitter AST analysis across 66 languages. Replaces dozens of file-read/grep cycles with sub-millisecond structured queries, cutting active tokens by 120× and turning codebase…
Content quality: CLI tool that grades text files against custom rulesets for AI slop, grammar, and technical doc quality using Jev scores and line-level flags, then guides an AI agent to auto-fix violations.
Google Labs' specification for describing visual identity systems to coding agents: machine-readable design tokens (YAML front matter) combined with human-readable design rationale (markdown prose) give agents a persistent, structured understanding of design constraints without requiring custom…
Compresses tool outputs, logs, files, and RAG chunks before they enter the context window, cutting active tokens by 60–95% without changing answers. Ships as a library, proxy, and MCP server — the right drop-in layer for any harness where bulky tool returns are the primary context pressure source.