Agenten stärken
Der eigene Befehl des Herausgebers. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
npx -y [email protected]Claude Code hat keinen Installationslink für einen lokalen Befehl. Kopieren Sie den Befehl unten und führen Sie ihn in einem Terminal aus.
claude mcp add agent-knowledge -- npx -y agent-knowledge@2.0.0In einem Terminal ausführen.
{ "mcpServers": { "agent-knowledge": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
Remote-URL oder ein Befehl auf Ihrem Rechner? Worin sich die beiden Installationen unterscheiden
Auf PlugMCP ausführen
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
StartenVom Herausgeber
Cross-session memory and recall for AI coding assistants -- works with Claude Code, Cursor, OpenCode, Cline, Continue.dev, and Aider out of the box. Git-synced knowledge base, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing.
Cross-session memory and recall for AI agents — git-synced knowledge base, knowledge graph, confidence scoring, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing
Benchmark: R@5 = 97.2% (sparse) / 98.8% (hybrid) on longmemeval_s and 86.0% (sparse) / 88.4% (hybrid) on the harder longmemeval_m split — the public LongMemEval academic benchmark (Wu et al. 2024, ICLR 2025), full 500 questions per split, no LLM, no API key, runs entirely offline. +8.6pp to +13.2pp R@5 over the paper's official flat-bm25 baseline in apples-to-apples reproduction. Full per-category table, reproduction instructions, and paper-comparison details in bench/README.md.
In Claude Code, the agent-knowledge plugin adds the /knowledge pane: the knowledge base beside the conversation. How it works, with pictures: the user manual.
AI coding sessions are ephemeral. When a session ends, everything it learned -- architecture decisions, debugging insights, project context -- is gone. The next session starts from scratch.
agent-knowledge solves this with two complementary systems:
Sessions from all major AI coding assistants are auto-discovered -- if a tool is installed, its sessions appear automatically.
No configuration needed. Additional session roots can be added via the AGENT_KNOWLEDGE_EXTRA_SESSION_ROOTS env var (comma-separated paths).
knowledge_analyze(action: "stale_by_code_activity") cross-references file paths mentioned in each entry body against filesModified in recent session summaries. Pairs with a symbol-presence precision layer: identifiers the entry quotes (inline backticks + fenced blocks) are checked in the touched file; if they still exist, confidence downweights ×0.3. Entries with evergreen: true are exempt.knowledge_analyze(action: "search_gaps") surfaces zero-result queries over the last since_days, grouped by token-Jaccard similarity. The clearest signal for "what entries should I write next?".knowledge(action: "wakeup") assembles a multi-section bundle (identity → active_tasks → recent_decisions → known_gotchas → last_session_summary → top_weighted → semantic_fallback) within a token budget (default 800, override via token_budget or AGENT_KNOWLEDGE_WAKEUP_BUDGET). Unused section budget redistributes to later sections.minScore, minRecallCount, minUniqueQueries). Runs automatically in background, on demand via knowledge_admin(action: "promote"), or benchable offline via npm run bench:promote. Emits an auditable .dreams/YYYY-MM-DD.md diary every run.SessionAdapter interfaceknowledge, knowledge_search, knowledge_session, knowledge_graph, knowledge_analyze, knowledge_admin)evergreen: true in frontmatter exempts an entry from decay in ranking AND makes it append-only under promotion. The /knowledge pane marks them.author: <string> frontmatter, kept with the entry and returned by the REST API.calls, imports, inherits edge types for code structure; directed BFS traversal (outbound/inbound/both); bulk_link for efficient ingestion; unlink_by_origin for clearing stale code edges before re-ingest; code: prefixed node IDs distinguish code from knowledgevalid_from / valid_to validity windows; as_of queries return point-in-time snapshots; invalidate action marks facts as ended without deleting themcategory_mode: "boost" so a wrong category guess down-ranks instead of discarding the right answerAGENT_KNOWLEDGE_INDEX_VERBATIM=falseknowledge_admin(action: "config") for runtime setup, persisted at XDG/AppData location/knowledge pane in Claude Code -- browse and search the knowledge base beside the conversation (agent-knowledge plugin)knowledge_analyze(action: "consolidate") for batch dedup scanningknowledge_analyze(action: "reflect") surfaces unconnected entries and generates structured prompts for the agent to identify new graph connectionsextracted (user-written) or inferred (auto-distilled, 0.85× search rank multiplier); confidence_score field carries the model's certainty 0-1knowledge_analyze actions god_nodes (most-connected entries), bridges (cross-category connectors), gaps (isolated entries)knowledge_analyze(action: "brief") returns a cached ~200 token summary (core concepts, active projects, recent decisions, stale and gap counts) for session-start orientationorigin (manual, auto-link, distill, reflect) so analysis can distinguish user judgment from automated heuristicsfreshness: { body_age_days, last_accessed, access_count, verified_at, verification_age_days, evergreen }. Agent reads the trust signal and decides; we impose no policy demotion.SessionStart auto-wakeup + ingest-freshness check, UserPromptSubmit first-prompt targeted injection, PreCompact memory-flush nudge + distill, SessionEnd distill. Six hook scripts total, all fail-open, each toggleable via an AGENT_KNOWLEDGE_* env var. See docs/HOOKS.md.~/.claude/projects/*/memory/, similar in other IDEs), route durable user facts and feedback to agent-knowledge instead. Auto-memory is machine-local and invisible to other machines; agent-knowledge is git-synced, cross-machine, searchable, and surfaces in wakeup. See the Claude Code integration note in docs/USER-MANUAL.md.The knowledge-ingest skill populates or updates the knowledge base from a codebase directory. It uses tree-sitter for zero-token structural extraction (classes, functions, imports, call graphs, rationale comments), then clusters files into subsystems and creates knowledge entries + graph edges via existing MCP tools. Subsequent runs are incremental — only changed files are reprocessed.
/knowledge-ingest ./my-project
Uses the Agent Skills standard — works with Claude Code, OpenCode, Cursor, Codex CLI, and Gemini CLI. See Ingestion Guide for details.
Supported languages: TypeScript, JavaScript, Python, Go, Rust, Java, C, C++.
npm install -g agent-knowledge
git clone https://github.com/keshrath/agent-knowledge.git
cd agent-knowledge
npm install && npm run build
Add to your MCP client config (Claude Code, Cline, etc.):
{
"mcpServers": {
"agent-knowledge": {
"command": "npx",
"args": ["agent-knowledge"]
}
}
}
The first MCP process also serves a local REST API on 127.0.0.1:3423 (what the hooks, the /knowledge pane and agent-tasks call); when it exits, another running session takes the port over.
See Setup Guide for client-specific instructions (Claude Code, Cursor, Windsurf, OpenCode).
claude plugin marketplace add keshrath/agent-knowledge
claude plugin install agent-knowledge@agent-knowledge
The plugin brings the MCP server, the knowledge-ingest skill and the /knowledge pane (Claude Code 2.1.289+).
Response shape: {mode: "general" | "scoped", sessions, knowledge}. Scoped mode returns knowledge: [] by design.
Scopes: errors, plans, configs, tools, files, decisions, all.
Search knobs:
mmr: true applies Maximal Marginal Relevance re-ranking (kills near-duplicate clusters in top-K). mmr_lambda 0-1, default 0.7.category_mode: "boost" (default) gives matching-category entries a 1.25× score multiplier instead of dropping non-matches. Pass "filter" for hard-filter behavior.explain: true attaches score_components: {bm25, decay, maturity, confidence, category_boost, mmr_penalty} to every knowledge hit.Knowledge types: related_to, supersedes, depends_on, contradicts, specializes, part_of, alternative_to, builds_on
Code structure types: calls, imports, inherits
Traverse directions: outbound (source→target), inbound (target→source), both (default, undirected)
Every project-level candidate is scored on six signals (relevance 0.30, frequency 0.24, query-diversity 0.15, recency 0.15, consolidation 0.10, conceptual-richness 0.06) and gated on minScore ≥ 0.5, minRecallCount ≥ 2, minUniqueQueries ≥ 2. All three gates must pass. Background auto-promotion is controlled by the same auto_distill config flag; invoke on demand with knowledge_admin(action: "promote").
promote_mode: "explain" (default) — score + gate candidates, write diary, DO NOT touch the KB.promote_mode: "apply" — promote candidates that pass, write diary, git-commit.~/agent-knowledge/.dreams/YYYY-MM-DD.md with per-candidate signal breakdowns and gate outcomes. The .-prefixed dir is git-tracked but excluded from list/search.evergreen: true frontmatter are never overwritten by promotion — activity is appended.Write-bench harness: npm run bench:promote — offline replay with auto-labeling by "referenced in later sessions". Compares gated promoter to a naive "ship all" baseline, reports precision / recall / F1. Use it to gate signal-weight or threshold changes before rolling them out.
Loopback only (127.0.0.1), JSON only. Every request goes through a guard: a foreign Host or any Origin header gets 403, a request body must be application/json. A :path with a slash is sent encoded (notes%2Fx.md).
graph LR
subgraph Storage
KB[(Knowledge Base<br/>~/agent-knowledge<br/>Git Repository)]
end
subgraph Session Sources
CC[(Claude Code<br/>JSONL)]
CU[(Cursor<br/>JSONL)]
OC[(OpenCode<br/>SQLite)]
CL[(Cline<br/>JSON)]
CD[(Continue.dev<br/>JSON)]
AI[(Aider<br/>MD / JSONL)]
end
subgraph agent-knowledge
KM[Knowledge Module<br/>store / search / git]
AD[Session Adapters<br/>auto-discovery]
SE[Search Engine<br/>TF-IDF + Fuzzy]
DS[REST API<br/>127.0.0.1:3423]
MCP[MCP Server<br/>stdio]
end
subgraph Clients
AG[Agent Sessions]
PN["/knowledge pane<br/>hooks, agent-tasks"]
end
KB <-->|git pull/push| KM
CC --> AD
CU --> AD
OC --> AD
CL --> AD
CD --> AD
AI --> AD
AD --> SE
KM --> MCP
SE --> MCP
KM --> DS
SE --> DS
MCP --> AG
DS --> PN
Entries and code symbols can be connected via typed, weighted edges stored in a dedicated edges SQLite table. Eleven relationship types are supported — 8 for knowledge edges and 3 for code structure:
Knowledge: related_to, supersedes, depends_on, contradicts, specializes, part_of, alternative_to, builds_on
Code structure: calls, imports, inherits
knowledge_graph(action: "link") creates or updates an edge (with optional strength 0-1)knowledge_graph(action: "unlink") removes edges (optionally filtered by type)knowledge_graph(action: "list") lists edges for an entry or relationship typeknowledge_graph(action: "traverse") performs directed BFS traversal from a starting entry. Supports direction (outbound, inbound, both) and rel_type filterknowledge_graph(action: "bulk_link") batch-creates edges in a single transaction (for code graph ingestion)knowledge_graph(action: "unlink_by_origin") deletes all edges with a specific origin (for clearing stale code edges before re-ingest)Code structure edges are created by the knowledge-ingest skill during codebase ingestion. They use code: prefixed node IDs:
code:src/auth/middleware.ts # file node
code:src/auth/middleware.ts::validateToken # symbol node
Query examples:
# Who calls validateToken?
knowledge_graph({ action: "traverse", entry: "code:src/auth.ts::validateToken", direction: "inbound", rel_type: "calls", depth: 3 })
# What breaks if I change this function?
knowledge_graph({ action: "traverse", entry: "code:src/auth.ts::validateToken", direction: "inbound", rel_type: "calls", depth: 5 })
# Combined: callers + knowledge context (decisions, design rationale)
knowledge_graph({ action: "traverse", entry: "code:src/auth.ts::validateToken", depth: 2 })
When knowledge with action: "write" creates or updates an entry, it automatically finds the top-3 most similar existing entries via cosine similarity and creates related_to edges for any pair scoring above 0.7.
Each knowledge entry has a confidence score tracked in the entry_scores SQLite table. Search results are ranked using:
finalScore = baseRelevance * 0.5^(daysSinceLastAccess / 90) * maturityMultiplier
Entries mature automatically based on access count:
Frequently accessed entries rise in search rankings; stale entries decay over time.
TF-IDF Ranking -- results scored by term frequency-inverse document frequency. Rare terms boost relevance. Global index cached for 60 seconds.
Fuzzy Matching -- Levenshtein edit distance with sliding window. Configurable threshold (default 0.7).
Scoped Recall via knowledge_search with the scope parameter:
POST /api/knowledge accepts { category, filename, content } and runs the full write pipeline: git pull → file write → embedding index → auto-link → git push → duplicate check. Returns { path, autoLinks?, duplicateWarnings?, git } with status 201.
This enables HTTP-based writes from other services without an MCP connection.
agent-tasks has a built-in KnowledgeBridge that auto-pushes learning and decision artifacts to agent-knowledge on task completion. Entries land in decisions/ with frontmatter tags (agent-tasks, project name, artifact type), are auto-indexed with embeddings, and auto-linked to similar entries. No configuration needed: while any session runs agent-knowledge, its REST API on 127.0.0.1:3423 answers.
npm test # 604 tests across 39 files
npm run test:watch # Watch mode
npm run lint # ESLint on src/ and tests/
npm run typecheck # tsc --noEmit
npm run check # typecheck + lint + format + test
All env vars live under the AGENT_KNOWLEDGE_* prefix. No host name is baked in — the adapter registry auto-detects installed AI coding hosts (.claude, .cursor, .codex, .aider, .continue, OpenCode) without configuration.
Project-scoped overrides win over the standard keys. Set either; the scoped form lets you run agent-knowledge with a different key than the rest of your environment.
Cross-session memory and recall for AI agents — git-synced knowledge base, knowledge graph, confidence scoring, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing
{ "mcpServers": { "agent-knowledge": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
Agent Knowledge läuft lokal über stdio.
Zuletzt geprüft: 2026-10-27. Cross-session memory and recall for AI agents — git-synced knowledge base, knowledge graph, confidence scoring, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing