thegian7 ~/catalog/…/team-intel$
‹theGian7

Persistent memory + governance for AI coding agents.

Hybrid search, verbatim recall, knowledge graph, and passive capture for Claude Code — local-first, and running in private beta. Works on Mac, Linux, and cloud. No hardware binding.

14 MCP Tools
Hybrid Search
Knowledge Graph
1,200+ Tests

Why AI coding agents forget.

Every team using Claude, Cursor, or Copilot has hit these four walls. team-intel answers each one with shipped code.

01 — Silent context death

Context compression hits mid-session.

“The model silently loses critical decisions made earlier in the conversation, then keeps generating with full confidence.”

Answer: hybrid search + verbatim recall. Every message is indexed in parallel with distilled extraction. When the top RRF score drops below the calibrated threshold, the RAG pipeline transparently falls back to raw message search. You search what was actually said, not just what was distilled.

02 — The cheerful yes-man

Frontier models agree with you 100% of the time.

“Even when you're wrong. Even when you contradicted yourself yesterday. The model has no memory of either.”

Answer: heuristic + gotcha artifacts retrieved by the same RAG pipeline. Saved insights push back with the user's prior corrections, not generic advice. A built-in reconciliation skill audits Claude memories against the knowledge base for drift.

03 — Anterograde amnesia

Every session is a blank slate.

“Frontier models cannot form long-term memories. Every new session, your team's hard-won context resets to zero.”

Answer: a passive capture hook records every tool use in under 10ms. A stop hook runs the extraction pipeline async, with a circuit breaker after three LLM failures. Knowledge survives across sessions, repositories, and machines.

04 — Zero governance

No enforced standards, no security scanning, no rules.

“The agent will happily merge insecure code, ignore your style guide, and forget last week's architectural decisions.”

Answer: shipped skills. /team-intel-backfill extracts institutional knowledge from git history. /refresh-claude-md audits CLAUDE.md against the actual code. /goodnight is an end-of-day sweep for uncommitted work and stale knowledge. Enforcement lives in skills and hooks, not LLM “please follow these rules” prose.

Three steps. Zero friction.

Knowledge capture that stays out of your way.

01
>_

Work Normally

Write code, debug, review PRs. Team Intel's capture hook runs in the background — less than 10ms overhead per tool call.

< 10ms overhead
02

Automatic Extraction

When your session ends, an LLM extracts structured knowledge: decisions you made, heuristics you discovered, playbooks you followed.

03

Instant Retrieval

Hybrid search (semantic + keyword + Reciprocal Rank Fusion) surfaces the right knowledge when you need it. Fresh results, not stale docs.

14 MCP Tools. Zero Overhead.

A complete knowledge management toolkit that integrates directly into your coding workflow.

team-intel — MCP tools
search_knowledge—Hybrid semantic + keyword search
save_insight—Capture decisions, heuristics, playbooks
ask_knowledge—Natural language Q&A with citations
get_context—Relevant knowledge for current file
link_knowledge—Map relationships between artifacts
browse_by_project—Discover knowledge by project
digest_files—Ingest markdown docs into the graph
...and 6 more

Hybrid Search

Semantic embeddings + BM25 keyword search fused with Reciprocal Rank Fusion. Get the best of both worlds — meaning and precision.

Knowledge Graph

A SQLite graph with temporal edges maps relationships between decisions, people, and projects. Discover connections you didn't know existed.

Freshness Scoring

Every artifact carries a freshness score — 90-day decay, nudged up when it’s used or validated — returned with each search result so agents can weigh old advice accordingly.

LLM-Agnostic

Works with Ollama (free, local), Claude API, or deferred extraction. Your choice of model, your data stays where you want it.

Explore a Knowledge Graph

This is a real knowledge graph generated from development sessions. Drag nodes, explore connections.

Decisions
Heuristics
Playbooks
Checklists

Stop losing what your team knows.

Knowledge should outlive Slack threads and quit notices.

Bus Factor

Know who knows what. Identify expertise gaps before they become crises. Every decision is linked to its author and context.

Onboarding

New team members can search what the team already decided before interrupting a senior.

Institutional Memory

Decisions outlive the people who made them. “Why did we choose Postgres?” is one search away.

What’s actually in the code.

No roadmap items. Everything below is in the codebase today.

Dimension team-intel
Install today Private beta — Mac, Linux, cloud, no hardware binding
Source availability Elastic License 2.0. Source shared with beta users; read, modify, and use it for yourself or your team
Test coverage 1,200+ tests across core, MCP, and platform
Persistence SQLite + ChromaDB (individual) or Postgres with tenant isolation (team)
Knowledge graph SQLite with temporal edges, entity registry, person aliases, merge primitives
Hybrid search Semantic (Qwen3-Embedding-8B) + BM25 fused with Reciprocal Rank Fusion (k=60)
Verbatim recall Every session message indexed in parallel with extraction. Calibrated RRF fallback when distilled artifacts miss
LLM flexibility Ollama, Claude API, or any OpenAI-compatible endpoint (vLLM, LiteLLM), plus deferred extraction
Pricing Free for individuals during the beta

Team Intel is in private beta.

Leave your email and I’ll reach out with access.

No spam. Beta invitations and launch updates only.

← the catalog·thegian7